Model reference: every language, image, video, audio and music model

Every model on the Omni API and the endpoint to call. For media models, put the fields listed here in input, or read them from GET /v1/models/{id}. See the API documentation for how each endpoint works and pricing for what calls cost.

Language models (96)
Image models with common fields (25)
Video models with common fields (1)
Image (63)
Video (81)
Lip-sync and avatars (8)
Upscaling (4)
Speech (7)
Audio tools (1)
Music suite (23)
Voice and audio endpoints (8)

Language models

OpenAI and Anthropic request formats, streaming supported. Call them on the endpoint shown; most also work on /v1/responses and /v1/messages, and the API returns a clear 400 when one does not.

Language models
Model	Made by	Endpoint
`aion-3.0`	omni	`POST /v1/chat/completions`
`aion-3.0-mini`	omni	`POST /v1/chat/completions`
`claude-fable-5`	anthropic	`POST /v1/chat/completions`
`claude-fable-5.1`	anthropic	`POST /v1/chat/completions`
`claude-haiku-4.5`	anthropic	`POST /v1/chat/completions`
`claude-haiku-5.5`	anthropic	`POST /v1/messages`
`claude-opus-4.5`	anthropic	`POST /v1/chat/completions`
`claude-opus-4.6`	anthropic	`POST /v1/chat/completions`
`claude-opus-4.7`	anthropic	`POST /v1/chat/completions`
`claude-opus-4.8`	anthropic	`POST /v1/chat/completions`
`claude-opus-4.8-fast`	anthropic	`POST /v1/chat/completions`
`claude-opus-5`	anthropic	`POST /v1/chat/completions`
`claude-opus-5-fast`	anthropic	`POST /v1/chat/completions`
`claude-opus-5.5`	anthropic	`POST /v1/chat/completions`
`claude-sonnet-4.5`	anthropic	`POST /v1/chat/completions`
`claude-sonnet-4.6`	anthropic	`POST /v1/chat/completions`
`claude-sonnet-5`	anthropic	`POST /v1/chat/completions`
`claude-sonnet-5.5`	anthropic	`POST /v1/chat/completions`
`deepseek-v4-flash`	deepseek	`POST /v1/chat/completions`
`deepseek-v4-flash-0731`	deepseek	`POST /v1/chat/completions`
`deepseek-v4-pro`	deepseek	`POST /v1/chat/completions`
`deepseek-v4-pro-0813`	deepseek	`POST /v1/chat/completions`
`deepseek-v4.1-flash`	deepseek	`POST /v1/chat/completions`
`gemini-2.5-flash`	google	`POST /v1/chat/completions`
`gemini-2.5-pro`	google	`POST /v1/chat/completions`
`gemini-3-flash`	google	`POST /v1/chat/completions`
`gemini-3-pro`	google	`POST /v1/chat/completions`
`gemini-3.1-flash-lite`	google	`POST /v1/chat/completions`
`gemini-3.1-pro`	google	`POST /v1/chat/completions`
`gemini-3.5-flash`	google	`POST /v1/chat/completions`
`gemini-3.5-flash-lite`	google	`POST /v1/chat/completions`
`gemini-3.6-flash`	google	`POST /v1/chat/completions`
`gemini-3.7-flash`	google	`POST /v1/chat/completions`
`gemini-3.8-flash`	google	`POST /v1/chat/completions`
`gemini-4-argon`	google	`POST /v1/chat/completions`
`gemma-3-12b-it`	google	`POST /v1/chat/completions`
`gemma-3-27b-it`	google	`POST /v1/chat/completions`
`gemma-3-4b-it`	google	`POST /v1/chat/completions`
`gemma-4-26b-a4b-it`	google	`POST /v1/chat/completions`
`gemma-4-31b-it`	google	`POST /v1/chat/completions`
`glm-4.5`	zhipu	`POST /v1/chat/completions`
`glm-4.5-air`	zhipu	`POST /v1/chat/completions`
`glm-4.6`	zhipu	`POST /v1/chat/completions`
`glm-4.7`	zhipu	`POST /v1/chat/completions`
`glm-4.7-flash`	zhipu	`POST /v1/chat/completions`
`glm-5`	zhipu	`POST /v1/chat/completions`
`glm-5.1`	zhipu	`POST /v1/chat/completions`
`glm-5.2`	zhipu	`POST /v1/chat/completions`
`glm-5.3`	zhipu	`POST /v1/chat/completions`
`glm-5.3-flash`	zhipu	`POST /v1/chat/completions`
`gpt-4.1-nano`	openai	`POST /v1/chat/completions`
`gpt-5-mini`	openai	`POST /v1/chat/completions`
`gpt-5-nano`	openai	`POST /v1/chat/completions`
`gpt-5.2`	openai	`POST /v1/chat/completions`
`gpt-5.2-codex`	openai	`POST /v1/chat/completions`
`gpt-5.4`	openai	`POST /v1/chat/completions`
`gpt-5.4-mini`	openai	`POST /v1/chat/completions`
`gpt-5.4-nano`	openai	`POST /v1/chat/completions`
`gpt-5.5`	openai	`POST /v1/chat/completions`
`gpt-5.5-pro`	openai	`POST /v1/chat/completions`
`gpt-5.6-luna`	openai	`POST /v1/chat/completions`
`gpt-5.6-sol`	openai	`POST /v1/chat/completions`
`gpt-5.6-terra`	openai	`POST /v1/chat/completions`
`gpt-6-astra`	openai	`POST /v1/chat/completions`
`gpt-6-luna`	openai	`POST /v1/chat/completions`
`gpt-6-sol`	openai	`POST /v1/chat/completions`
`gpt-6.1-sol`	openai	`POST /v1/chat/completions`
`gpt-oss-120b`	openai	`POST /v1/chat/completions`
`grok-4.3`	xai	`POST /v1/chat/completions`
`grok-4.5`	xai	`POST /v1/chat/completions`
`grok-4.6`	xai	`POST /v1/chat/completions`
`grok-4.7`	xai	`POST /v1/chat/completions`
`jev-1.13`	omni	`POST /v1/chat/completions`
`kimi-k2-thinking`	moonshot	`POST /v1/chat/completions`
`kimi-k2.5`	moonshot	`POST /v1/chat/completions`
`kimi-k3`	moonshot	`POST /v1/chat/completions`
`mimo-v2.6-flash`	xiaomi	`POST /v1/chat/completions`
`mimo-v2.6-pro`	xiaomi	`POST /v1/chat/completions`
`minimax-m2`	minimax	`POST /v1/chat/completions`
`minimax-m2.1`	minimax	`POST /v1/chat/completions`
`minimax-m2.5`	minimax	`POST /v1/chat/completions`
`minimax-m2.7`	minimax	`POST /v1/chat/completions`
`minimax-m3`	minimax	`POST /v1/chat/completions`
`muse-spark-1.2`	meta	`POST /v1/chat/completions`
`qwen3-32b`	alibaba	`POST /v1/chat/completions`
`qwen3-coder-30b-a3b-instruct`	alibaba	`POST /v1/chat/completions`
`qwen3-coder-next`	alibaba	`POST /v1/chat/completions`
`qwen3-next-80b-a3b-instruct`	alibaba	`POST /v1/chat/completions`
`qwen3-vl-235b-a22b-instruct`	alibaba	`POST /v1/chat/completions`
`qwen3.5-35b-a3b`	alibaba	`POST /v1/chat/completions`
`qwen3.6-27b`	alibaba	`POST /v1/chat/completions`
`qwen3.6-35b-a3b`	alibaba	`POST /v1/chat/completions`
`qwen3.8-2.4t-a95b`	alibaba	`POST /v1/chat/completions`
`qwen3.8-27b`	alibaba	`POST /v1/chat/completions`
`qwen3.8-flash`	alibaba	`POST /v1/chat/completions`
`qwen3.8-max`	alibaba	`POST /v1/chat/completions`

Image models with common fields

These take the common image fields: prompt, aspect_ratio or size, resolution, n and reference_urls. GET /v1/models/{id} shows each one’s aspect ratios, resolutions and reference limits, and POST /v1/images/quote gives the price before you run it.

Image models with common fields
Model	Made by	Endpoint
`bytedance-seedream-4`	bytedance	`POST /v1/images/generations`
`bytedance-seedream-4.5`	bytedance	`POST /v1/images/generations`
`bytedance-seedream-5-lite`	bytedance	`POST /v1/images/generations`
`bytedance-seedream-5-pro`	bytedance	`POST /v1/images/generations`
`flux-1-kontext`	black-forest-labs	`POST /v1/images/generations`
`flux-2-pro`	black-forest-labs	`POST /v1/images/generations`
`gemini-2.5-flash-image`	google	`POST /v1/images/generations`
`gemini-3-pro-image-preview`	google	`POST /v1/images/generations`
`gemini-3.1-flash-image-preview`	google	`POST /v1/images/generations`
`gemini-3.1-flash-lite-image`	google	`POST /v1/images/generations`
`gpt-image-1`	openai	`POST /v1/images/generations`
`gpt-image-1.5`	openai	`POST /v1/images/generations`
`gpt-image-2`	openai	`POST /v1/images/generations`
`gpt-image-2.5-flare`	openai	`POST /v1/images/generations`
`gpt-image-2.5-sunburst`	openai	`POST /v1/images/generations`
`grok-imagine`	xai	`POST /v1/images/generations`
`kling-omni-image`	kuaishou	`POST /v1/images/generations`
`krea-2-large`	krea	`POST /v1/images/generations`
`krea-2-medium`	krea	`POST /v1/images/generations`
`nano-banana`	google	`POST /v1/images/generations`
`recraft-v4`	recraft	`POST /v1/images/generations`
`recraft-v4.1`	recraft	`POST /v1/images/generations`
`runway-gen4-image`	runway	`POST /v1/images/generations`
`runway-gen4-image-turbo`	runway	`POST /v1/images/generations`
`wan-2.5-preview-image`	alibaba	`POST /v1/images/generations`

Video models with common fields

These take prompt, image_urls, aspect_ratio, duration and resolution, and return the video in one call.

Video models with common fields
Model	Made by	Endpoint
`seedance-2.0`	bytedance	`POST /v1/videos/generations`

Image

bytedance/seedream · Seedream3.0 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the image (Max length: 5000 characters)
`image_size`	string	Output size preset. One of square, square_hd, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Default: `square_hd`.
`guidance_scale`	number	Controls how closely the output image aligns with the input prompt. Higher values mean stronger prompt correlation. (Min: 1, Max: 10, Step: 0.1) (step: 0.1) Default: `2.5`.
`seed`	integer	Random seed to control the stochasticity of image generation.

bytedance/seedream-v4-edit · Seedream4.0 - Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to edit the image (Max length: 5000 characters)
`image_urls` (required)	array	List of URLs of input images for editing. Presently, up to 10 image inputs are allowed. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`image_size`	string	The size of the generated image. Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_3_2`, `portrait_16_9`, `landscape_4_3`, `landscape_3_2`, `landscape_16_9`, `landscape_21_9`. Default: `square_hd`.
`image_resolution`	string	Final image resolution is determined by combining image_size (aspect ratio) and image_resolution (pixel scale).. Allowed: `1K`, `2K`, `4K`. Default: `1K`.
`max_images`	number	Set this value (1–6) to cap how many images a single generation run can produce in one set—because they’re created in one shot rather than separate requests, you must also state the exact number you want in the prompt so both settings align. (Min: 1, Max: 6, Step: 1) (step: 1) Default: `1`.
`seed`	integer	Random seed for reproducible results. Integer, up to 1000000. Omit for a random seed.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedream-v4-text-to-image · Seedream4.0 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the image (Max length: 5000 characters)
`image_size`	string	The size of the generated image. Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_3_2`, `portrait_16_9`, `landscape_4_3`, `landscape_3_2`, `landscape_16_9`, `landscape_21_9`. Default: `square_hd`.
`image_resolution`	string	Final image resolution is determined by combining image_size (aspect ratio) and image_resolution (pixel scale).. Allowed: `1K`, `2K`, `4K`. Default: `1K`.
`max_images`	number	Set this value (1–6) to cap how many images a single generation run can produce in one set—because they’re created in one shot rather than separate requests, you must also state the exact number you want in the prompt so both settings align. (Min: 1, Max: 6, Step: 1) (step: 1) Default: `1`.
`seed`	integer	Random seed for reproducible results. Integer, up to 1000000. Omit for a random seed.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

flux-2/flex-image-to-image · Flux-2 - Image to Image · POST /v1/images/generations

Field	Type	Details
`input_urls` (required)	array	Input reference images (1-8 images). (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`prompt` (required)	string	Must be between 3 and 5000 characters. (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio for the generated image. Select 'auto' to match the first input image ratio (requires input image). Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, `auto`.
`resolution` (required)	string	Required. Output image resolution. Allowed: `1K`, `2K`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

flux-2/flex-text-to-image · Flux-2 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Generation prompt, length must be between 3-5000 characters. (Maximum length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio of the generated image. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`.
`resolution` (required)	string	Required. Output image resolution. Allowed: `1K`, `2K`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

flux-2/pro-image-to-image · Flux-2 - Pro Image to Image · POST /v1/images/generations

Field	Type	Details
`input_urls` (required)	array	Input reference images (1-8 images). (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`prompt` (required)	string	Must be between 3 and 5000 characters. (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio for the generated image. Select 'auto' to match the first input image ratio (requires input image). Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, `auto`.
`resolution` (required)	string	Required. Output image resolution. Allowed: `1K`, `2K`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

flux-2/pro-text-to-image · Flux-2 - Pro Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Must be between 3 and 5000 characters. (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio for the generated image. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`.
`resolution` (required)	string	Required. Output image resolution. Allowed: `1K`, `2K`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

flux-kontext · Generate or Edit Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired image or edit. Required for both generation and editing modes. - Should be detailed and specific - For image editing, describe the desired changes - For image generation, describe the complete scene - IMPORTANT: Only English language is supported
`model`	string	Model tier: flux-kontext-pro (default) or flux-kontext-max (higher quality, higher price). Allowed: `flux-kontext-pro`, `flux-kontext-max`. Default: `flux-kontext-pro`.
`enable_translation`	boolean	Whether to enable automatic translation feature. - Since prompt only supports English, when this parameter is true, the system will automatically translate non-English prompts to English - If your prompt is already in English, you can set this to false - Default value: true
`upload_cn`	boolean	(Optional) Specifies the server region for image upload. Set to true to use servers in China, false to use non-China servers. Choose based on your geographical location for optimal upload speeds.
`input_image`	string	URL of the input image for editing mode. Required when editing an existing image. - Must be a valid image URL - Image must be accessible to the API server
`aspect_ratio`	string	Output image aspect ratio. You Applicable in both text-to-image generation and image editing modes. For text-to-image generation , the output image will follow the specified aspect ratio. For image editing , if aspect_ratio is provided, the edited image will follow that ratio. If not provided, the image will retain its original aspect ratio. Supported Aspect Ratios: \| Ratio \| Format Type \| Allowed: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`.
`output_format`	string	Output image format. Allowed: `jpeg`, `png`. Default: `jpeg`.
`prompt_upsampling`	boolean	- If true, performs upsampling on the prompt - May increase processing time Default: `false`.
`safety_tolerance`	integer	For Image Generation Mode: Moderation level for inputs and outputs. Value ranges from 0 (most strict) to 6 (more permissive). For Image Editing Mode: Moderation level for inputs and outputs. Value ranges from 0 (most strict) to 2 (balanced). Default: 2 Allowed: `0`, `1`, `2`, `3`, `4`, `5`, `6`. Default: `2`.
`watermark`	string	Watermark identifier to add to the generated image. - Optional - If provided, a watermark will be added to the output image

google/imagen4 · Google - imagen4 · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing what you want to see (Max length: 5000 characters)
`negative_prompt`	string	A description of what to discourage in the generated images (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio of the output image: 1:1, 16:9, 9:16, 3:4, 4:3 or auto. Allowed: `1:1`, `16:9`, `9:16`, `3:4`, `4:3`, `auto`.
`seed`	string	Random seed for reproducible generation (Max length: 500 characters)

google/imagen4-fast · Google - imagen4-fast · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing what you want to see (Max length: 5000 characters)
`negative_prompt`	string	A description of what to discourage in the generated images (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio of the output image: 1:1, 16:9, 9:16, 3:4, 4:3 or auto. Allowed: `1:1`, `16:9`, `9:16`, `3:4`, `4:3`, `auto`.
`seed`	integer	Random seed for reproducible generation

google/imagen4-ultra · Google - imagen4-ultra · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing what you want to see (Max length: 5000 characters)
`negative_prompt`	string	A description of what to discourage in the generated images (Max length: 5000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio of the output image: 1:1, 16:9, 9:16, 3:4, 4:3 or auto. Allowed: `1:1`, `16:9`, `9:16`, `3:4`, `4:3`, `auto`.
`seed`	string	Random seed for reproducible generation (Max length: 500 characters)

google/nano-banana · Google - Nano Banana · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt for image generation (Max length: 20000 characters)
`output_format`	string	Output format for the images Allowed: `png`, `jpeg`. Default: `png`.
`aspect_ratio`	string	Aspect ratio of the output image. Set this field explicitly. Allowed: `1:1`, `9:16`, `16:9`, `3:4`, `4:3`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`, `auto`.
`image_size`	string	The aspect ratio of the generated image (this parameter has been replaced by aspect_ratio; please use the latest aspect_ratio parameter). Allowed: `1:1`, `9:16`, `16:9`, `3:4`, `4:3`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`, `auto`. Default: `1:1`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

google/nano-banana-edit · Google - Nano Banana Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt for image editing (Max length: 20000 characters)
`image_urls` (required)	array	List of URLs of input images for editing,up to 10 images. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`output_format`	string	Output format for the images Allowed: `png`, `jpeg`. Default: `png`.
`aspect_ratio`	string	Aspect ratio of the output image. Set this field explicitly. Allowed: `1:1`, `9:16`, `16:9`, `3:4`, `4:3`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`, `auto`.
`image_size`	string	The aspect ratio of the generated image (this parameter has been replaced by aspect_ratio; please use the latest aspect_ratio parameter). Allowed: `1:1`, `9:16`, `16:9`, `3:4`, `4:3`, `3:2`, `2:3`, `5:4`, `4:5`, `21:9`, `auto`. Default: `1:1`.

gpt-4o-image · Generate 4o Image · POST /v1/images/generations

Field	Type	Details
`prompt`	string	(Optional) Text prompt that conveys the creative idea you want the 4o model to render. Required if neither `files_url` nor `file_url` is supplied. At least one of `prompt` or `files_url` must be provided.
`files_url`	array	(Optional) Up to 5 publicly reachable image URLs to serve as reference or source material. Use this when you want to edit or build upon an existing picture. If you don’t have reliable hosting, upload your images first via our File Upload API quick‑start: Supported formats: .jfif, .pjpeg, .jpeg, .pjp, .jpg, .png, .webp. At least one of `prompt` or `files_url` must be provided.
`size` (required)	string	(Required) Aspect ratio of the generated image. Must be one of the listed values. Allowed: `1:1`, `3:2`, `2:3`.
`file_url`	string	(Optional, Deprecated) File URL, such as an image URL. If file_url is provided, 4o image may create based on this image. This parameter will be deprecated in the future, please use files_url instead.

gpt-image-2-5-flare-image-to-image · GPT Image 2.5 Flare - Image To Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompts, up to 20,000 characters.
`input_urls`	array	Array of input image URLs.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. The 27:16, 16:27, 9:8 and 8:9 aspect ratios support 1K only. 2K and 4K are available for other aspect ratios. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `27:16`, `16:27`, `9:8`, `8:9`.
`resolution`	string	Image resolution Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Allowed: `transparent`, `opaque`, `auto`.

gpt-image-2-5-flare-text-to-image · GPT Image 2.5 Flare - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt. Required, maximum 20,000 characters.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. The 27:16, 16:27, 9:8 and 8:9 aspect ratios support 1K only. 2K and 4K are available for other aspect ratios. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `27:16`, `16:27`, `9:8`, `8:9`.
`resolution`	string	Image resolution Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Allowed: `transparent`, `opaque`, `auto`.

gpt-image-2-5-sunburst-image-to-image · GPT Image 2.5 Sunburst - Image To Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompts, up to 20,000 characters.
`input_urls`	array	Array of input image URLs.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. The 27:16, 16:27, 9:8 and 8:9 aspect ratios support 1K only. 2K and 4K are available for other aspect ratios. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `27:16`, `16:27`, `9:8`, `8:9`.
`resolution`	string	Image resolution Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Allowed: `transparent`, `opaque`, `auto`.

gpt-image-2-5-sunburst-text-to-image · GPT Image 2.5 Sunburst - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt. Required, maximum 20,000 characters.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. The 27:16, 16:27, 9:8 and 8:9 aspect ratios support 1K only. 2K and 4K are available for other aspect ratios. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `27:16`, `16:27`, `9:8`, `8:9`.
`resolution`	string	Image resolution Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Allowed: `transparent`, `opaque`, `auto`.

gpt-image-2-image-to-image · GPT Image 2 - Image To Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompts, up to 20,000 characters.
`input_urls`	array	Array of input image URLs.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. Note: for 2K resolution, the following aspect ratios are not supported: 5:4, 4:5, 3:1, 1:3, and 9:21. for 4K resolution, the following aspect ratios are not supported: 3:1, 1:3, and 9:21. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `5:4`, `4:5`, `16:9`, `9:16`, `2:1`, `1:2`, `3:1`, `1:3`, `21:9`, `9:21`.
`resolution`	string	Output resolution: 1K, 2K or 4K. Set this field explicitly. 2K does not support 5:4, 4:5, 3:1, 1:3 or 9:21; 4K does not support 3:1, 1:3 or 9:21. The background parameter is only available at 1K. Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Note: This parameter is only supported when the resolution is 1K. Allowed: `transparent`, `opaque`, `auto`.

gpt-image-2-text-to-image · GPT Image-2 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt. Required, maximum 20,000 characters.
`aspect_ratio`	string	The aspect ratio of the generated image is set to auto by default. Note: for 2K resolution, the following aspect ratios are not supported: 5:4, 4:5, 3:1, 1:3, and 9:21. for 4K resolution, the following aspect ratios are not supported: 3:1, 1:3, and 9:21. Allowed: `auto`, `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `5:4`, `4:5`, `16:9`, `9:16`, `2:1`, `1:2`, `3:1`, `1:3`, `21:9`, `9:21`.
`resolution`	string	Output resolution: 1K, 2K or 4K. Set this field explicitly. 2K does not support 5:4, 4:5, 3:1, 1:3 or 9:21; 4K does not support 3:1, 1:3 or 9:21. The background parameter is only available at 1K. Allowed: `1K`, `2K`, `4K`.
`background`	string	Image background Note: This parameter is only supported when the resolution is 1K. Allowed: `transparent`, `opaque`, `auto`.

gpt-image/1.5-image-to-image · GPT Image-1.5 - Image to Image · POST /v1/images/generations

Field	Type	Details
`input_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`prompt` (required)	string	A text description of the image you want to generate
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `2:3`, `3:2`.
`quality` (required)	string	Required. Quality: medium=balanced, high=slow/detailed. Allowed: `medium`, `high`.

gpt-image/1.5-text-to-image · GPT Image-1.5 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `2:3`, `3:2`.
`quality` (required)	string	Required. Quality: medium=balanced, high=slow/detailed. Allowed: `medium`, `high`.

grok-imagine-image-2-0/image-edit · Grok Imagine Image 2.0 Image Edit · POST /v1/images/generations

Field	Type	Details
`prompt`	string	A text description specifying the desired content or style of the generated image. Up to 8,000 characters.
`aspect_ratio` (required)	string	Specifies the width-to-height ratio of the generated image. Controls the aspect ratio of the output. This field is required. Allowed: `1:1`, `2:3`, `3:2`, `16:9`, `9:16`, `auto`.
`image_urls` (required)	array	An array containing up to 5 and at least 1 URL strings pointing to a reference image.

grok-imagine-image-2-0/segment-edit · Grok Imagine Image 2.0 Segment Edit · POST /v1/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired image. Up to 65,000 characters.
`task_id` (required)	string	The source task ID to use for image editing(This can be a task ID generated by the `grok-imagine-image-2-0/text-to-image` model, or a task ID generated by the `grok-imagine-image-2-0/segment-map` model by passing an `image_url`.).
`mask_indexs`	array	Indexes of the segments to edit, taken from resultObject.segments[].index of the segment-map task (0-based). Example: [0, 2].

grok-imagine-image-2-0/segment-map · Grok Imagine Image 2.0 Segment Map · POST /v1/generations

No input fields beyond the prompt.

grok-imagine-image-2-0/text-to-image · Grok Imagine Image 2.0 Text To Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired image. This field is required. Up to 8,000 characters.
`aspect_ratio` (required)	string	Specifies the width-to-height ratio of the generated image. Controls the aspect ratio of the output. This field is required. Allowed: `1:1`, `2:3`, `3:2`, `16:9`, `9:16`.

grok-imagine/image-to-image · Grok Imagine - image to image · POST /v1/images/generations

Field	Type	Details
`prompt`	string	A text description specifying the desired content or style of the generated image. (Max length: 390000 characters)
`image_urls` (required)	array	1–5 image URLs. (Use file URLs after upload, not raw file content. Accepted types: image/jpeg, image/png, image/webp. Max size: 10.0MB per image.) In your prompt, reference the uploaded image by typing @image(n) followed by a space (for example: @image1 a sunset over the ocean).
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

grok-imagine/text-to-image · Grok Imagine - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired image. Required field. - Should be detailed and specific about the desired visual elements - Describe composition, style, lighting, mood, and other visual details - Maximum length: 5000 characters - Supports English language prompts
`aspect_ratio` (required)	string	Required. Aspect ratio of the output image: 2:3, 3:2, 1:1, 16:9, 9:16. Allowed: `2:3`, `3:2`, `1:1`, `16:9`, `9:16`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.
`enable_pro`	boolean	Controls the request processing strategy. - `false`: Corresponds to speed mode. The system prioritizes response time and throughput, suitable for latency-sensitive scenarios. - `true`: Corresponds to quality mode. The system prioritizes processing quality and precision, suitable for scenarios requiring higher accuracy.

ideogram/character · Ideogram - Character · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt describing the scene to generate with the referenced character. (Max length: 5000 characters)
`reference_image_urls` (required)	array	A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`rendering_speed`	string	The rendering speed to use. Default value: "BALANCED" Allowed: `TURBO`, `BALANCED`, `QUALITY`. Default: `BALANCED`.
`style`	string	The style type to generate with. Default value: "AUTO" Allowed: `AUTO`, `REALISTIC`, `FICTION`. Default: `AUTO`.
`expand_prompt`	boolean	Determine if MagicPrompt should be used in generating the request or not. Default value: true (Boolean value (true/false))
`num_images`	string	Number of images to generate. Allowed: `1`, `2`, `3`, `4`. Default: `1`.
`image_size`	string	The resolution of the generated image Default value: square_hd Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Default: `square_hd`.
`seed`	integer	Seed for the random number generator
`negative_prompt`	string	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: "" (Max length: 5000 characters)

ideogram/character-edit · Ideogram - Character Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to fill the masked part of the image. (Max length: 5000 characters)
`image_url` (required)	string	The image URL to generate an image from. Should have the same aspect ratio as the mask. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`mask_url` (required)	string	The mask URL to inpaint the image. Should have the same aspect ratio as the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`reference_image_urls` (required)	array	A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`rendering_speed`	string	The rendering speed to use. Default value: "BALANCED" Allowed: `TURBO`, `BALANCED`, `QUALITY`. Default: `BALANCED`.
`style`	string	The style type to generate with. Default value: "AUTO" Allowed: `AUTO`, `REALISTIC`, `FICTION`. Default: `AUTO`.
`expand_prompt`	boolean	Determine if MagicPrompt should be used in generating the request or not. Default value: true (Boolean value (true/false))
`num_images`	string	Number of images to generate. Allowed: `1`, `2`, `3`, `4`. Default: `1`.
`seed`	integer	Seed for the random number generator

ideogram/character-remix · Ideogram - Character Remix · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to remix the image with (Max length: 5000 characters)
`image_url` (required)	string	The image URL to remix (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`reference_image_urls` (required)	array	A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`rendering_speed`	string	The rendering speed to use. Default value: "BALANCED" Allowed: `TURBO`, `BALANCED`, `QUALITY`. Default: `BALANCED`.
`style`	string	The style type to generate with. Default value: "AUTO" Allowed: `AUTO`, `REALISTIC`, `FICTION`. Default: `AUTO`.
`expand_prompt`	boolean	Determine if MagicPrompt should be used in generating the request or not. Default value: true (Boolean value (true/false))
`image_size`	string	Output image size. Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Default: `square_hd`.
`num_images`	string	Number of images to generate. Allowed: `1`, `2`, `3`, `4`. Default: `1`.
`seed`	integer	Seed for the random number generator
`strength`	number	Strength of the input image in the remix Default value: 0.8 (Min: 0.1, Max: 1, Step: 0.1) (step: 0.1) Default: `0.8`.
`negative_prompt`	string	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: "" (Max length: 500 characters)
`image_urls`	array	A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`reference_mask_urls`	string	A set of masks to apply to the character references. Currently only 1 mask is supported, rest will be ignored. (maximum total size 10MB across all character references). The masks should be in JPEG, PNG or WebP format (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)

ideogram/v3-edit · Ideogram V3 Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to fill the masked part of the image. Maximum length: 5000 characters.
`image_url` (required)	string	The image URL to generate an image from. Needs to match the dimensions of the mask. - Please provide the URL of the uploaded file, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 10.0MB
`mask_url` (required)	string	The mask URL to inpaint the image. Needs to match the dimensions of the input image. - Please provide the URL of the uploaded file, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 10.0MB
`rendering_speed`	string	The rendering speed to use. Default value: `BALANCED`. - `TURBO`: Turbo - `BALANCED`: Balanced - `QUALITY`: Quality Allowed: `TURBO`, `BALANCED`, `QUALITY`. Default: `BALANCED`.
`expand_prompt`	boolean	Determine if MagicPrompt should be used in generating the request or not. Default value: `true`. - Boolean value: `true` / `false` Default: `true`.
`seed`	integer	Seed for the random number generator.

ideogram/v3-remix · Ideogram V3 Remix · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to remix the image with. Maximum length: 5000 characters.
`image_url` (required)	string	The image URL to remix. - Please provide the URL of the uploaded file, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 10.0MB
`rendering_speed`	string	The rendering speed to use. - `TURBO`: Turbo - `BALANCED`: Balanced - `QUALITY`: Quality Allowed: `TURBO`, `BALANCED`, `QUALITY`.
`style`	string	The style type to generate with. - `AUTO`: Auto - `GENERAL`: General - `REALISTIC`: Realistic - `DESIGN`: Design Allowed: `AUTO`, `GENERAL`, `REALISTIC`, `DESIGN`.
`expand_prompt`	boolean	Determine if MagicPrompt should be used in generating the request or not. - Boolean value: `true` / `false`
`image_size`	string	The resolution of the generated image. - `square`: Square - `square_hd`: Square HD - `portrait_4_3`: Portrait 3:4 - `portrait_16_9`: Portrait 9:16 - `landscape_4_3`: Landscape 4:3 - `landscape_16_9`: Landscape 16:9 Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`.
`num_images`	string	Number of images to generate. - `1`: 1 image - `2`: 2 images - `3`: 3 images - `4`: 4 images Allowed: `1`, `2`, `3`, `4`.
`seed`	integer	Seed for the random number generator.
`strength`	number	Strength of the input image in the remix. - Minimum: `0.01` - Maximum: `1` - Step: `0.01`
`negative_prompt`	string	Description of what to exclude from the generated image. If the positive prompt conflicts with the negative prompt, the positive prompt takes precedence. Maximum length: 5000 characters.

ideogram/v3-text-to-image · Ideogram V3 Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Description of the image to generate. Maximum length: 5000 characters.
`rendering_speed`	string	The rendering speed to use. - `TURBO`: Turbo - `BALANCED`: Balanced - `QUALITY`: Quality Allowed: `TURBO`, `BALANCED`, `QUALITY`.
`style`	string	The style type to generate with. - `AUTO`: Auto - `GENERAL`: General - `REALISTIC`: Realistic - `DESIGN`: Design Allowed: `AUTO`, `GENERAL`, `REALISTIC`, `DESIGN`.
`expand_prompt`	boolean	Determines whether MagicPrompt should be used to enhance the generation request. - Boolean value: `true` / `false`
`image_size`	string	The resolution of the generated image. - `square`: Square - `square_hd`: Square HD - `portrait_4_3`: Portrait 3:4 - `portrait_16_9`: Portrait 9:16 - `landscape_4_3`: Landscape 4:3 - `landscape_16_9`: Landscape 16:9 Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`.
`seed`	integer	Seed for the random number generator.
`negative_prompt`	string	Description of what to exclude from the generated image. If the positive prompt conflicts with the negative prompt, the positive prompt takes precedence. Maximum length: 5000 characters.

nano-banana-2 · Google - Nano Banana 2 · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 20000 characters)
`image_input`	array	Input images to transform or use as reference (supports up to 10 images) (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio`	string	Aspect ratio of the generated image Allowed: `1:1`, `2:3`, `3:2`, `1:4`, `4:1`, `3:4`, `4:3`, `4:5`, `5:4`, `1:8`, `8:1`, `9:16`, `16:9`, `21:9`, `auto`. Default: `auto`.
`resolution`	string	Resolution of the generated image Allowed: `1K`, `2K`, `4K`. Default: `1K`.
`output_format`	string	Format of the output image Allowed: `png`, `jpg`. Default: `jpg`.

nano-banana-2-1 · Google - Nano Banana 2.1 · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 20000 characters)
`image_input`	array	Input images to transform or use as reference (supports up to 10 images) (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio`	string	Aspect ratio of the generated image Allowed: `1:1`, `2:3`, `3:2`, `1:4`, `4:1`, `3:4`, `4:3`, `4:5`, `5:4`, `1:8`, `8:1`, `9:16`, `16:9`, `21:9`, `auto`. Default: `auto`.
`resolution`	string	Resolution of the generated image Allowed: `1K`, `2K`, `4K`. Default: `1K`.
`output_format`	string	Format of the output image Allowed: `png`, `jpg`. Default: `jpg`.

nano-banana-2-lite · Google - Nano Banana 2 Lite · POST /v1/images/generations

Field	Type	Details
`image_urls`	array	Input image URL array. Optional parameter. Set to an empty array or omit it for pure text-to-image generation. Supports up to 10 images. - Please provide uploaded file URLs, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 30.0MB
`prompt` (required)	string	Text prompt used to generate the image. Required. Maximum length: 20000 characters.
`aspect_ratio` (required)	string	Required. Aspect ratio of the output image. Use "auto" to let the model decide. Allowed: `1:1`, `1:4`, `1:8`, `2:3`, `3:2`, `3:4`, `4:1`, `4:3`, `4:5`, `5:4`, `8:1`, `9:16`, `16:9`, `21:9`, `auto`.

nano-banana-pro · Google - Nano Banana Pro · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 20000 characters)
`image_input`	array	Input images to transform or use as reference (supports up to 8 images) (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio`	string	Aspect ratio of the generated image Allowed: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`, `auto`. Default: `1:1`.
`resolution`	string	Resolution of the generated image Allowed: `1K`, `2K`, `4K`. Default: `1K`.
`output_format`	string	Output image format: png or jpg. Set this field explicitly. Allowed: `png`, `jpg`.

qwen/image-edit · Qwen - Image Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to generate the image with (Max length: 2000 characters)
`image_url` (required)	string	The URL of the image to edit. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`acceleration`	string	Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. Default value: "none" Allowed: `none`, `regular`, `high`. Default: `none`.
`image_size`	string	The size of the generated image. Default value: landscape_4_3 Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Default: `landscape_4_3`.
`num_inference_steps`	number	The number of inference steps to perform. Default value: 30 (Min: 2, Max: 49, Step: 1) (step: 1) Default: `25`.
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.
`guidance_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Default value: 4 (Min: 0, Max: 20, Step: 0.1) (step: 0.1) Default: `4`.
`num_images`	string	num_images Allowed: `1`, `2`, `3`, `4`.
`enable_safety_checker`	boolean	If set to true, the safety checker will be enabled. Default value: true (Boolean value (true/false))
`output_format`	string	The format of the generated image. Default value: "png" Allowed: `jpeg`, `png`. Default: `png`.
`negative_prompt`	string	The negative prompt for the generation Default value: " " (Max length: 500 characters)
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen/image-to-image · Qwen - Image to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to generate the image with (Max length: 5000 characters)
`image_url` (required)	string	The reference image to guide the generation (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`strength`	number	Denoising strength. 1.0 = fully remake; 0.0 = preserve original (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0.8`.
`output_format`	string	The format of the generated image Allowed: `png`, `jpeg`. Default: `png`.
`acceleration`	string	Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text Allowed: `none`, `regular`, `high`. Default: `none`.
`negative_prompt`	string	The negative prompt for the generation (Max length: 500 characters)
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time
`num_inference_steps`	number	The number of inference steps to perform (Min: 2, Max: 250, Step: 1) (step: 1) Default: `30`.
`guidance_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you (Min: 0, Max: 20, Step: 0.1) (step: 0.1) Default: `2.5`.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen/text-to-image · Qwen - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to generate the image with (Max length: 5000 characters)
`image_size`	string	The size of the generated image. Set this field explicitly. Allowed: `square`, `square_hd`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`.
`num_inference_steps`	number	The number of inference steps to perform (Min: 2, Max: 250, Step: 1) (step: 1) Default: `30`.
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time
`guidance_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you (Min: 0, Max: 20, Step: 0.1) (step: 0.1) Default: `2.5`.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`output_format`	string	The format of the generated image Allowed: `png`, `jpeg`. Default: `png`.
`negative_prompt`	string	The negative prompt for the generation (Max length: 500 characters)
`acceleration`	string	Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text Allowed: `none`, `regular`, `high`. Default: `none`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen2-1/image-to-image · Qwen 2.1 - Image to Image · POST /v1/images/generations

Field	Type	Details
`image_urls` (required)	array	Reference images, given as an array of 1 to 10 http(s) URLs. Required. The order of the array is the order the prompt refers to ("the first image", "the second image"). JPEG, PNG and WebP are supported, up to 30MB and 25MP each, and every URL must be directly retrievable with a GET. If an image URL cannot be fetched, the task fails with failCode 400. With more than 10 entries the request is reject
`prompt` (required)	string	The prompt describing the result you want. Required. Any language is supported, up to 5000 characters; if it is longer, the request is rejected. When `mask_url` is supplied, use it to describe what should be generated inside the white area of the mask.
`mask_url`	string	Inpainting mask that switches the request into local-edit mode. A black and white image where white marks the area to change and black is kept unchanged, with a few pixels of feathering along the boundary. It must be used with exactly one entry in `image_urls`, otherwise the request is rejected. The mask should have the same aspect ratio as that reference image; a mask of a different size is s
`aspect_ratio`	string	Output aspect ratio. Defaults to `auto`, which takes the aspect ratio of the first reference image and snaps it to the nearest supported ratio. The actual pixel size also depends on `resolution`. Ignored in local-edit mode. Allowed: `auto`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`, `16:9`, `9:16`, `21:9`, `9:21`. Default: `auto`.
`resolution`	string	Output resolution tier. `1K` is the faster option; `2K` produces four times the pixels and takes considerably longer, up to about 3 minutes with reference images. Only `1K` and `2K` are accepted — with any other value, including `4K`, the request is rejected. Allowed: `1K`, `2K`. Default: `1K`.
`background`	string	Background type. transparent outputs a PNG or WebP with a real alpha channel and cannot be used with JPEG. When using transparent, describe only the subject — prompts that mention a background, scene, surface, etc. may produce a non-transparent result. Allowed: `opaque`, `transparent`. Default: `opaque`.
`output_format`	string	Output image format. `png` (default) and `webp` both carry an alpha channel and can be used with `background: transparent`. `jpeg` has no alpha channel and cannot be combined with a transparent background. Allowed: `png`, `webp`, `jpeg`. Default: `png`.
`enhance_prompt`	boolean	Rewrites the prompt into a fuller scene description before generating, which noticeably improves quality. Enabled by default (also when the parameter is omitted); pass false to turn it off. Default: `true`.
`seed`	integer	The random seed. Omit it to generate with a random seed. Passing the same seed together with the same prompt and parameters reproduces the same image within the same service version.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen2-1/text-to-image · Qwen 2.1 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt that describes the image content, style and composition you want to generate. Required. Any language is supported, up to 5000 characters; if it is longer, the request is rejected.
`aspect_ratio`	string	The output aspect ratio. Default `1:1`. The actual pixel size also depends on `resolution`. Allowed: `1:1`, `4:3`, `3:4`, `3:2`, `2:3`, `16:9`, `9:16`, `21:9`, `9:21`. Default: `1:1`.
`resolution`	string	The output resolution tier. `1K` is the faster option; `2K` produces four times the pixels and takes longer. Only `1K` and `2K` are accepted — with any other value, including `4K`, the request is rejected. Allowed: `1K`, `2K`. Default: `1K`.
`background`	string	Background type. transparent outputs a PNG or WebP with a real alpha channel and cannot be used with JPEG. When using transparent, describe only the subject — prompts that mention a background, scene, surface, etc. may produce a non-transparent result. Allowed: `opaque`, `transparent`. Default: `opaque`.
`output_format`	string	The output image format. `png` (default) and `webp` both carry an alpha channel and can be used with `background: transparent`. `jpeg` has no alpha channel and cannot be combined with a transparent background. Allowed: `png`, `webp`, `jpeg`. Default: `png`.
`enhance_prompt`	boolean	Rewrites the prompt into a fuller scene description before generating, which noticeably improves quality. Enabled by default (also when the parameter is omitted); pass false to turn it off. Default: `true`.
`seed`	integer	The random seed. Omit it to generate with a random seed. Passing the same seed together with the same prompt and parameters reproduces the same image within the same service version.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen2/image-edit · Qwen2 - Image Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to generate the image with (Max length: 800 characters)
`image_url` (required)	array	URLs of the images to edit. Supports up to 3 images. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`image_size`	string	The size of the generated image. Default value: 16:9 Allowed: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `9:16`, `16:9`, `21:9`. Default: `16:9`.
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `jpeg`, `png`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen2/text-to-image · Qwen2 - Text To Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The prompt to generate the image with. Max length: 5000 characters.
`image_size`	string	The size of the generated image. Default value: 16:9 Allowed: `1:1`, `3:4`, `4:3`, `9:16`, `16:9`. Default: `16:9`.
`seed`	integer	The same seed and the same prompt given to the same version of the model will output the same image every time.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `jpeg`, `png`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

qwen3/image-to-image · Qwen3 Image to Image · POST /v1/images/generations

Field	Type	Details
`image_urls` (required)	array	Input image URL array. Upload images and provide their URLs rather than the file content. Supports up to 3 images. Supported file types: `image/jpeg`, `image/png`, `image/webp`, `image/bmp`, and `image/gif`,`image/tiff`. Maximum file size: 10 MB per image.
`prompt` (required)	string	The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
`resolution`	string	The output image resolution. Allowed: `1K`, `2K`. Default: `1K`.
`image_size`	string	The output image size. Allowed: `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`. Default: `16:9`.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `png`, `jpeg`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. Default: `true`.
`negative_prompt`	string	The negative prompt that describes content you do not want to appear in the image.
`seed`	integer	Random seed, 0–2147483647. If omitted, a random seed is used.
`nsfw_checker`	boolean	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures. Default: `false`.

qwen3/pro-image-to-image · Qwen3 Pro Image to Image · POST /v1/images/generations

Field	Type	Details
`image_urls` (required)	array	Input image URL array. Upload images and provide their URLs rather than the file content. Supports up to 3 images. Supported file types: `image/jpeg`, `image/png`, `image/webp`, `image/bmp`, and `image/gif`,`image/tiff`. Maximum file size: 10 MB per image.
`prompt` (required)	string	The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
`resolution`	string	The output image resolution. Allowed: `1K`, `2K`. Default: `1K`.
`image_size`	string	The output image size. Allowed: `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`. Default: `16:9`.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `png`, `jpeg`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. Default: `true`.
`negative_prompt`	string	The negative prompt that describes content you do not want to appear in the image.
`seed`	integer	Random seed, 0–2147483647. If omitted, a random seed is used.
`nsfw_checker`	boolean	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures. Default: `false`.

qwen3/pro-text-to-image · Qwen3 Pro Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
`resolution`	string	The output image resolution. Allowed: `1K`, `2K`.
`image_size`	string	The output image size. Allowed: `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`. Default: `16:9`.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `png`, `jpeg`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. Default: `true`.
`negative_prompt`	string	The negative prompt that describes content you do not want to appear in the image.
`seed`	integer	Random seed, 0–2147483647. If omitted, a random seed is used.
`nsfw_checker`	boolean	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures. Default: `false`.

qwen3/text-to-image · Qwen3 Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported.
`resolution`	string	The output image resolution. Allowed: `1K`, `2K`.
`image_size`	string	The output image size. Allowed: `1:1`, `3:2`, `2:3`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`. Default: `16:9`.
`output_format`	string	Output format: png or jpeg. Set this field explicitly. Allowed: `png`, `jpeg`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. Default: `true`.
`negative_prompt`	string	The negative prompt that describes content you do not want to appear in the image.
`seed`	integer	Random seed, 0–2147483647. If omitted, a random seed is used.
`nsfw_checker`	boolean	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures. Default: `false`.

recraft/remove-background · Recraft - Remove Background · POST /v1/generations

Field	Type	Details
`image` (required)	string	Image to remove background from. Supported formats: PNG, JPG, WEBP. Max 5MB, max 16MP, max dimension 4096px, min dimension 256px. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 5.0MB)

seedream/4.5-edit · Seedream4.5 - Edit · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 3000 characters)
`image_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 2K images, while High outputs 4K images. Allowed: `basic`, `high`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/4.5-text-to-image · Seedream4.5 - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 3000 characters)
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 2K images, while High outputs 4K images. Allowed: `basic`, `high`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-flash-image-to-image · Seedream5.0 Flash - Image to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–5000 characters.
`image_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`size`	string	Resolution level of the output image. Allowed: `1K`, `1.5K`, `2K`. Default: `1K`.
`output_format`	string	Output image format. Set this field explicitly. Allowed: `png`, `jpeg`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-flash-layer-decomposition · Seedream5.0 Flash - Layer Decomposition · POST /v1/generations

Field	Type	Details
`prompt`	string	Optional prompt for layer separation. - When a prompt is provided, the model separates the specified elements based on the prompt - When no prompt is provided, the model automatically identifies the main elements in the image - Supports using ` x1 y1 x2 y2 ` to precisely specify element positions, recommending the use of normalized coordinates in the 0-1000 range - Length: 4–5000 characters
`image_url` (required)	string	The source image URL for layer separation. - Must upload exactly 1 image - Supported formats: PNG, JPEG. - Image size must not exceed 30 MB - Total pixel range is 262,144-36,000,000 - Aspect ratio range is 1:16-16:1
`size`	string	Resolution level of the output image. The base image maintains the aspect ratio of the input image, and each separated layer maintains the aspect ratio of the corresponding element in the original image. - `auto`: Automatically selected based on the input image size - `1K`: 1K resolution level - `1.5K`: 1.5K resolution level - `2K`: 2K resolution level Allowed: `auto`, `1K`, `1.5K`, `2K`. Default: `auto`.
`output_format`	string	Output format of the base image. This parameter only controls the base image format; all separated layers are fixed to output as PNG. Allowed: `png`, `jpeg`. Default: `jpeg`.

seedream/5-flash-text-to-image · Seedream5.0 Flash - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–5000 characters.
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`size`	string	Resolution level of the output image. Allowed: `1K`, `1.5K`, `2K`. Default: `1K`.
`output_format`	string	Output image format. Set this field explicitly. Allowed: `png`, `jpeg`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-lite-image-to-image · Seedream5.0 Lite - Image to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–2995 characters.
`image_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 2K images, while High outputs 3K images, and Ultra outputs 4K images. Allowed: `basic`, `high`, `ultra`.
`output_format`	string	Output image format. Set this field explicitly. Allowed: `png`, `jpeg`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-lite-text-to-image · Seedream5.0 Lite - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–2995 characters.
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 2K images, while High outputs 3K images, and Ultra outputs 4K images. Allowed: `basic`, `high`, `ultra`.
`output_format`	string	Output image format. Set this field explicitly. Allowed: `png`, `jpeg`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-pro-image-to-image · Seedream5.0 Pro - Image to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–5000 characters.
`image_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 30.0MB)
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 1K images, while High outputs 2K images. Allowed: `basic`, `high`.
`output_format`	string	Format of the output image Allowed: `png`, `jpeg`. Default: `png`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

seedream/5-pro-layer-decomposition · Seedream5.0 Pro - Layer Decomposition · POST /v1/generations

Field	Type	Details
`prompt`	string	Optional prompt for layer separation. - When a prompt is provided, the model separates the specified elements based on the prompt - When no prompt is provided, the model automatically identifies the main elements in the image - Supports using ` x1 y1 x2 y2 ` to precisely specify element positions, recommending the use of normalized coordinates in the 0-1000 range
`image_url` (required)	string	The source image URL for layer separation. - Must upload exactly 1 image - Supported formats: PNG, JPEG. - Image size must not exceed 30 MB - Total pixel range is 262,144-36,000,000 - Aspect ratio range is 1:16-16:1
`size` (required)	string	Required. Output resolution tier: auto, 1K, 1.5K or 2K. auto follows the input image size. Allowed: `auto`, `1K`, `1.5K`, `2K`.
`output_format`	string	Output format of the base image. This parameter only controls the base image format; all separated layers are fixed to output as PNG. Allowed: `png`, `jpeg`. Default: `jpeg`.

seedream/5-pro-text-to-image · Seedream5.0 Pro - Text to Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Text prompt, 4–5000 characters.
`aspect_ratio` (required)	string	Required. Width-height ratio of the image, determining its visual form. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Basic outputs 1K images, while High outputs 2K images. Allowed: `basic`, `high`.
`output_format`	string	Format of the output image Allowed: `png`, `jpeg`. Default: `png`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-image · Wan 2.7 Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Prompt for image generation or editing. This field supports both Chinese and English, with a maximum length of 5000 characters.
`input_urls`	array	(Optional) Array of input image URLs.
`aspect_ratio`	string	(Optional) Output aspect ratio when no image input is provided. Allowed: `1:1`, `16:9`, `4:3`, `21:9`, `3:4`, `9:16`, `8:1`, `1:8`.
`enable_sequential`	boolean	Whether to enable sequential/group image mode. Default is false. Default: `false`.
`n`	integer	Number of images to generate. Range is 1-4 when `enable_sequential=false` (default: 4); range is 1-12 when `enable_sequential=true` (default: 12).
`resolution`	string	Output resolution: 1K or 2K (default 2K). For 4K, use wan/2-7-image-pro. Allowed: `1K`, `2K`. Default: `2K`.
`thinking_mode`	boolean	Whether to enable thinking mode. Only available when `enable_sequential=false` and `input_urls` is empty; it is disabled in other cases. Default: `false`.
`color_palette`	array	(Optional) Custom color theme. Only available when `enable_sequential=false`. Requires 3-10 colors, 8 recommended.
`bbox_list`	array	(Optional) Interactive editing bounding box areas. The outer list length should match `input_urls`; maximum 2 boxes per image; single box format is `[x1, y1, x2, y2]`.
`watermark`	boolean	Whether to add watermark. Default: `false`.
`seed`	integer	Optional. Omit for a random seed.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-image-pro · Wan 2.7 Image Pro · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	Prompt for image generation or editing. This field supports both Chinese and English, with a maximum length of 5000 characters.
`input_urls`	array	(Optional) Array of input image URLs.
`aspect_ratio`	string	(Optional) Output aspect ratio when no image input is provided. Allowed: `1:1`, `16:9`, `4:3`, `21:9`, `3:4`, `9:16`, `8:1`, `1:8`.
`enable_sequential`	boolean	Whether to enable sequential/group image mode. Default is false. Default: `false`.
`n`	integer	Number of images to generate. Range is 1-4 when `enable_sequential=false` (default: 4); range is 1-12 when `enable_sequential=true` (default: 12).
`resolution`	string	Output resolution: 1K, 2K or 4K (default 2K). 4K is available only for text-to-image (no input images) with sequential generation off. Allowed: `1K`, `2K`, `4K`. Default: `2K`.
`thinking_mode`	boolean	Whether to enable thinking mode. Only available when `enable_sequential=false` and `input_urls` is empty; it is disabled in other cases. Default: `false`.
`color_palette`	array	(Optional) Custom color theme. Only available when `enable_sequential=false`. Requires 3-10 colors, 8 recommended.
`bbox_list`	array	(Optional) Interactive editing bounding box areas. The outer list length should match `input_urls`; maximum 2 boxes per image; single box format is `[x1, y1, x2, y2]`.
`watermark`	boolean	Whether to add watermark. Default: `false`.
`seed`	integer	Optional. Omit for a random seed.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

z-image · Z-Image · POST /v1/images/generations

Field	Type	Details
`prompt` (required)	string	A text description of the image you want to generate (Max length: 1000 characters)
`aspect_ratio` (required)	string	Required. Aspect ratio for the generated image. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Video

bytedance/seedance-1.5-pro · Bytedance Seedance 1.5 Pro · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)
`input_urls`	array	URLs of input images for image-to-video generation. Optional field. - Accepts 0-2 images - If not provided, the model will perform text-to-video generation - File URLs after upload, not file content - Accepted types: image/jpeg, image/png, image/webp - Max size per image: 10.0MB
`aspect_ratio` (required)	string	Required. One of 1:1, 4:3, 3:4, 16:9, 9:16, 21:9. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`duration` (required)	number	Required. Output length in whole seconds, 4–12.
`fixed_lens`	boolean	Seedance adds dynamic camera movement. Enable this feature to lock the camera for stable, static shots. - true: Lock camera for static shots - false: Allow dynamic camera movement Default: `false`.
`generate_audio`	boolean	Whether to generate synchronized audio. Default: true. Pass false for a silent video. Audio doubles the per-second price. Default: `true`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedance-2 · bytedance-seedance-2 · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)
`first_frame_url`	string	First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`last_frame_url`	string	End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`reference_image_urls`	array	Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single image requirements: Format: jpeg, png, webp, bmp, tiff, gif. Aspect ratio (width/height): (0.4, 2.5) Width and height (px): (300, 6000) Size: Single image less than 30 MB. Up to 9 images.
`reference_video_urls`	array	Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single video requirements: Video format: mp4, mov. Resolution: 480p, 720p Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds. Dimensions: Aspect ratio (width/height): [0.4, 2.5] Width/height (px): [300, 6000] Total pixels: [64
`reference_audio_urls`	array	Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single audio requirements: Format: wav, mp3 Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s. Size: Single audio file size not exceeding 15 MB.
`return_last_frame`	boolean	Whether to return the last frame of the video as an image. Default: `false`.
`generate_audio`	boolean	Whether to generate audio for the video. - true: Generate with audio - false: Generate without audio Default: `true`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance, 1080p for High-quality video, 4K Ultra-High Definition, delivering perfect visual details. 4k output is 3840×2160 encoded as H.265 (HEVC); other resolutions are H.264. Make sure your player or pipeline supports HEVC. Allowed: `480p`, `720p`, `1080p`, `4k`. Default: `720p`.
`aspect_ratio`	string	Video aspect ratio configuration. Required field. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `adaptive`. Default: `16:9`.
`duration`	integer	Video duration in 4-15 seconds or -1. Default: `5`.
`web_search`	boolean	Use online search. Text-to-video only.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedance-2-5 · Bytedance Seedance 2.5 · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	The text prompt used to generate the video.. ( Max length: 20480 characters)
`first_frame_url`	string	First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) Cannot be used simultaneously with reference_image_urls, reference_video_urls, or reference_audio_urls.
`last_frame_url`	string	End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj) last_frame_url cannot be passed alone; first_frame_url must be provided together with it.
`reference_image_urls`	array	Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single image requirements: Format: jpeg, png, webp. Aspect ratio (width/height): (0.4, 2.5) Width and height (px): (300, 6000) Size: Single image less than 30 MB. Up to 30 images. Mutually exclusive with the first/last-frame scenario;
`reference_video_urls`	array	Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single video requirements: Video format: mp4, mov, mkv. Resolution: 480p, 720p Dimensions: Aspect ratio (width/height): [0.4, 2.5] Width/height (px): [300, 6000] Total pixels: [640×640=409600, 834×1112=927408], i.e., the product of width and height must meet the range requirement of [409600, 927408]
`reference_audio_urls`	array	Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj) . Single audio requirements: Format: wav, mp3, aac, ogg Size: Single audio file size not exceeding 15 MB. Single audio duration: [2, 30] seconds; mutually exclusive with first/last frames; total duration of reference audio must not exceed 30 seconds.
`return_last_frame`	boolean	Whether to also return the last frame of the generated video as a JPEG (in resultJson.lastFrameUrl). Default false. Default: `false`.
`generate_audio`	boolean	Whether to generate audio synchronized with the video. Default: true. Default: `true`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance. Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`aspect_ratio`	string	Video aspect ratio configuration. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `adaptive`. Default: `adaptive`.
`duration`	integer	Video duration in 4-30 seconds. Special values -1: Pass -1 for automatic duration selection — the model picks a suitable duration itself (for video-editing tasks, it matches the input video's length; for other task types, it selects within the valid range), instead of you specifying an exact value. Default: `5`.
`output_format`	string	Video output format. Allowed: `mp4`, `mov`. Default: `mp4`.
`web_search`	boolean	Enable online search.
`draft`	boolean	Enable draft mode. When enabled, only 480p resolution is allowed. Draft task ID is valid for 7 days from draft creation. Default: `false`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedance-2-5-draft · Bytedance Seedance 2.5 Draft · POST /v1/videos/generations

Field	Type	Details
`draft_task_id` (required)	string	task id from model seedance 2.5 generation task. Valid for 7 days from draft creation.
`resolution` (required)	string	output video resolution. Allowed: `1080p`.
`output_format`	string	ouput video format. Allowed: `mp4`, `mov`.
`return_last_frame`	boolean	Whether to also return the last frame of the generated video as a JPEG (in resultJson.lastFrameUrl). Default false. Default: `false`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedance-2-fast · Bytedance Seedance 2.0 Fast · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)
`first_frame_url`	string	First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`last_frame_url`	string	End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`reference_image_urls`	array	Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single image requirements: Format: jpeg, png, webp, bmp, tiff, gif. Aspect ratio (width/height): (0.4, 2.5) Width and height (px): (300, 6000) Size: Single image less than 30 MB. Up to 9 images.
`reference_video_urls`	array	Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single video requirements: Video format: mp4, mov. Resolution: 480p, 720p Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds. Dimensions: Aspect ratio (width/height): [0.4, 2.5] Width/height (px): [300, 6000] Total pixels: [640
`reference_audio_urls`	array	Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single audio requirements: Format: wav, mp3 Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s. Size: Single audio file size not exceeding 15 MB.
`return_last_frame`	boolean	Whether to return the last frame of the video as an image. Default: `false`.
`generate_audio`	boolean	Whether to generate audio for the video. - true: Generate with audio - false: Generate without audio Default: `true`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance Allowed: `480p`, `720p`. Default: `720p`.
`aspect_ratio`	string	Video aspect ratio configuration. Required field. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `adaptive`. Default: `16:9`.
`duration`	integer	Video duration in 4-15 seconds or -1. Default: `5`.
`web_search`	boolean	Use online search. Text-to-video only.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/seedance-2-mini · Bytedance Seedance 2.0 Mini · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	The text prompt used to generate the video. Required field. (Min length: 3, Max length: 20000 characters)
`first_frame_url`	string	First frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`last_frame_url`	string	End frame image url or asset://{assetId} (for example: asset://asset-20260404242101-76djj)
`reference_image_urls`	array	Enter a list of image URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single image requirements: Format: jpeg, png, webp, gif. Aspect ratio (width/height): (0.4, 2.5) Width and height (px): (300, 6000) Size: Single image less than 30 MB. Up to 9 images.
`reference_video_urls`	array	Enter a list of video URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single video requirements: Video format: mp4, mov. Resolution: 480p, 720p Duration: Single video duration [2, 15] s, maximum 3 reference videos, total duration of all videos not exceeding 15 seconds. Dimensions: Aspect ratio (width/height): [0.4, 2.5] Width/height (px): [300, 6000] Total pixels: [640
`reference_audio_urls`	array	Enter a list of audio URLs or asset://{assetId} (for example: asset://asset-20260404242101-76djj). Single audio requirements: Format: wav, mp3 Duration: Single audio duration [2, 15] s, maximum 3 reference audios, total duration of all audios not exceeding 15 s. Size: Single audio file size not exceeding 15 MB.
`generate_audio`	boolean	Whether to generate audio for the video. - true: Generate with audio - false: Generate without audio Default: `true`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance Allowed: `480p`, `720p`. Default: `720p`.
`aspect_ratio`	string	Video aspect ratio configuration. Required field. Allowed: `1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `21:9`, `adaptive`. Default: `16:9`.
`duration`	integer	Video duration in 4-15 seconds or -1. Default: `5`.
`web_search`	boolean	Use online search. Text-to-video only.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/v1-lite-image-to-video · Bytedance - V1 Lite Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video (Max length: 10000 characters)
`image_url` (required)	string	The URL of the image used to generate video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`resolution`	string	Video resolution - 480p for faster generation, 720p for higher quality Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`duration`	string	Duration of the video in seconds Allowed: `5`, `10`. Default: `5`.
`camera_fixed`	boolean	Whether to fix the camera position (Boolean value (true/false))
`seed`	number	Random seed to control video generation. Use -1 for random. (Min: -1, Max: 2147483647, Step: 1) (step: 1) Default: `-1`.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`end_image_url`	string	The URL of the image the video ends with. Defaults to None. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/v1-lite-text-to-video · Bytedance - V1 Lite Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video (Max length: 10000 characters)
`aspect_ratio`	string	The aspect ratio of the generated video Allowed: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `9:21`. Default: `16:9`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for higher quality Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`duration`	string	Duration of the video in seconds Allowed: `5`, `10`. Default: `5`.
`camera_fixed`	boolean	Whether to fix the camera position (Boolean value (true/false))
`seed`	integer	Random seed to control video generation. Use -1 for random.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/v1-pro-fast-image-to-video · Bytedance V1 Pro Fast Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video (Max length: 10000 characters)
`image_url` (required)	string	The URL of the image used to generate video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`resolution`	string	Output resolution: 720p or 1080p. Allowed: `720p`, `1080p`. Default: `720p`.
`duration`	string	Duration of the video in seconds Allowed: `5`, `10`. Default: `5`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/v1-pro-image-to-video · Bytedance V1 Pro Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video (Max length: 10000 characters)
`image_url` (required)	string	The URL of the image used to generate video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`duration`	string	Duration of the video in seconds Allowed: `5`, `10`. Default: `5`.
`camera_fixed`	boolean	Whether to fix the camera position (Boolean value (true/false))
`seed`	number	Random seed to control video generation. Use -1 for random. (Min: -1, Max: 2147483647, Step: 1) (step: 1) Default: `-1`.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

bytedance/v1-pro-text-to-video · Bytedance - V1 Pro Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used to generate the video (Max length: 10000 characters)
`aspect_ratio`	string	The aspect ratio of the generated video Allowed: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`. Default: `16:9`.
`resolution`	string	Video resolution - 480p for faster generation, 720p for balance, 1080p for higher quality Allowed: `480p`, `720p`, `1080p`. Default: `720p`.
`duration`	string	Duration of the video in seconds Allowed: `5`, `10`. Default: `5`.
`camera_fixed`	boolean	Whether to fix the camera position (Boolean value (true/false))
`seed`	number	Random seed to control video generation. Use -1 for random. (Min: -1, Max: 2147483647, Step: 1) (step: 1) Default: `-1`.
`enable_safety_checker`	boolean	The safety checker is always enabled in Playground. It can only be disabled by setting false through the API. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

gemini-omni-video · Gemini Omni Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Video prompt used to describe the target content, style, camera language, or character actions in the generated video.
`image_urls`	array	Array of image URLs. You can provide one or more reference images for characters, scenes, styles, or storyboard guidance. Image limits: - Each file must be no larger than `20MB` - Use publicly accessible image URLs - Max 7 images
`audio_ids`	array	Array of audio IDs generated by the `gemini-omni-audio` endpoint. Useful for narration, dialogue, music, or audio guidance in the generated video. Max 3 items.
`video_list`	array	Array of video clips. Each item defines a source video and the trim range to use during generation. Video limits: - Each file must be no larger than `100MB` - Video duration must not exceed `30s` - `ends` should be greater than `start` - The difference between the end time and the start time must not exceed `10s`. - Max 1 items. Equal 2 images
`character_ids`	array	An array of character IDs generated by the `gemini-omni-character` API. Used to provide character appearance, identity, or person references for the video. Up to 3 character IDs. Each uses 1 image slot (2 if created with portrait + body images). Total slots (images + videos × 2 + character slots) ≤ 7.
`duration` (required)	string	The duration of the generated video in seconds. Available values are 4, 6, 8, and 10. When video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect.Note: when video input is provided, the output duration is determined by the model automatically. This duration parameter will not take effect. Allowed: `4`, `6`, `8`, `10`.
`aspect_ratio`	string	The aspect ratio of the generated video. `16:9` is landscape, and `9:16` is portrait. Allowed: `16:9`, `9:16`.
`resolution`	string	The resolution of the generated video. Available values are 720p, 1080p, and 4k. Allowed: `720p`, `1080p`, `4k`. Default: `720p`.
`seed`	integer	Random seed. Range: [0, 2147483647]. If not specified, the system generates a seed automatically. Fixing the seed can improve reproducibility, but results may still vary due to the model’s stochasticity.

google/gemini-omni-flash-1-1 · Gemini Omni 1.1 Flash · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The video prompt, used to describe the visual content, style, cinematography, or character actions of the target video.
`image_urls`	array	An array of image URLs. Multiple reference images can be uploaded to provide references for characters, scenes, styles, or storyboards. Image limitations: - Each file must not exceed `20MB` - Use publicly accessible image URLs - Maximum of 7 images - Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.
`first_frame_url`	string	The URL of the first-frame image. Used to specify the starting frame of the generated video. Note: This field is mutually exclusive with `image_urls`, `audio_ids`, `video_list`, and `character_ids` and cannot be provided at the same time.
`last_frame_url`	string	The URL of the last-frame image. Used to specify the ending frame of the generated video. Note: The last-frame image cannot be used alone and must be provided together with the first-frame image (`first_frame_url`).
`audio_ids`	array	An array of audio IDs generated by the `gemini-omni-audio` interface. Used to provide narration, dialogue, background music, or sound references for the video. Up to 3 items. Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and cannot be provided at the same time.
`video_list`	array	An array of video clips. Each element describes a video asset that can be used for generation and its trimming time range. Video limitations: - Each file must not exceed `100MB` - Video duration must not exceed `30s` - `ends` should be greater than `start` - The difference between the end and start times must not exceed `10s` - Maximum of 1 item, occupying two image slots - Note: This field is mut
`character_ids`	array	An array of character IDs generated by the `gemini-omni-character` interface. Used to provide character appearance, identity, or person references for the video. Up to 3 character IDs. Each uses 1 image slot (2 if created with portrait + body images). Total slots (images + videos × 2 + character slots) ≤ 7. Note: This field is mutually exclusive with the first-frame image (`first_frame_url`) and c
`duration` (required)	string	The duration of the generated video, in seconds. Valid values are 4, 6, 8, and 10. This parameter only takes effect when there is no video input. If video input is used, the output duration is determined by the model, and the `duration` parameter will be ignored. Note: When video input is provided, the output duration is automatically determined by the model. In this case, the `duration` parameter Allowed: `4`, `6`, `8`, `10`.
`aspect_ratio`	string	The aspect ratio of the generated video. `16:9` is landscape, and `9:16` is portrait. Allowed: `16:9`, `9:16`.
`resolution`	string	The resolution of the generated video. Valid values are 360p, 720p, 1080p, and 4k. Allowed: `360p`, `720p`, `1080p`, `4k`. Default: `720p`.
`seed`	integer	The random seed. Valid range: [0, 2147483647]. If not specified, the system will automatically generate a seed. A fixed seed can improve result reproducibility, but because the model itself is stochastic, results may still vary.

grok-imagine-video-1-5-preview · Grok Imagine Video 1.5 Preview · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Prompt for video generation. Maximum length: 4096 characters.
`image_urls`	array	Upload image files to be used as API input. Supported file types: image/jpeg, image/png, image/webp, image/jpg. Maximum file size: 20MB. Supports multi-file upload, up to 7 file.Only one is supported when the resolution is 1080p.
`aspect_ratio`	string	The aspect ratio of the video. This parameter is invalid if it is a single image. Allowed: `1:1`, `16:9`, `9:16`, `3:2`, `2:3`, `auto`. Default: `auto`.
`resolution`	string	Resolution for video generation. Allowed: `480p`, `720p`, `1080p`. Default: `480p`.
`duration`	integer	Video duration in seconds. Range: [1, 15]. Default: 8. Minimum: 1. Maximum: 15. Step: 1. Default: `8`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

grok-imagine/extend · Grok Imagine - Video Extend · POST /v1/videos/generations

Field	Type	Details
`task_id` (required)	string	Task ID from a previously successful video generation task. Required field. - task_id must be a successful grok-imagine/text-to-video or grok-imagine/image-to-video task. - The original video generation must have completed successfully - Only Omni AI–generated task IDs are supported
`prompt` (required)	string	Text instructions describing the required movement of the video. Required field. - Provide a detailed description of how you would like the video to expand and continue. - You can specify camera movements, scene changes, object actions, etc. - The more specific the prompt words are, the more likely the generated effect will match your expectations. - Supports input in both Chinese and English.
`extend_at` (required)	number	Required. Time point in the source video, in seconds (minimum 2), from which the extension starts. Default: `2`.
`extend_times` (required)	string	6 or 10 (seconds). Allowed: `6`, `10`.

grok-imagine/image-to-video · Grok Imagine Image to Video · POST /v1/videos/generations

Field	Type	Details
`image_urls`	array	Provide an external image URL as a reference for video generation. Up to 7 images are supported. Do not use it simultaneously with task_id. In your prompt, reference an uploaded image by typing @image(n) followed by a space (for example: @image1 a sunset over the ocean). - Supports JPEG, PNG, and WEBP formats - Maximum file size for each image: 10MB - The Spicy mode is not available when using ext
`task_id`	string	Task ID from a previously generated Grok image. Use with index to select a specific image. Do not use with image_urls. - Use task ID from grok-imagine/text-to-image generations - Supports all modes including Spicy - Maximum length: 100 characters
`index`	integer	When using task_id, the 0-based index of the image to use. A grok-imagine/text-to-image task returns 2 images, so valid values are 0 and 1. Default 0. - Ignored if image_urls is provided Default: `0`.
`prompt`	string	Text prompt describing the desired video motion. Optional field. - Should be detailed and specific about the desired visual motion - Describe movement, action sequences, camera work, and timing - Include details about subjects, environments, and motion dynamics - Maximum length: 5000 characters - Supports English language prompts
`mode`	string	Specifies the generation mode affecting the style and intensity of motion. Note: Spicy mode is not available for external image inputs. - fun: More creative and playful interpretation - normal: Balanced approach with good motion quality - spicy: More dynamic and intense motion effects (not available for external images) Default: normal Allowed: `fun`, `normal`, `spicy`. Default: `normal`.
`duration`	string	The duration of the generated video (in seconds) (6-30). (Minimum: 6, Maximum: 30, Step: 1)
`resolution`	string	The resolution of the generated video. Allowed: `480p`, `720p`, `1080p`. Default: `480p`.
`aspect_ratio`	string	Image ratio selection only applies to multi-image generation mode. In single-image mode, the video width and height are referenced to the image width and height. Allowed: `2:3`, `3:2`, `1:1`, `16:9`, `9:16`. Default: `16:9`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

grok-imagine/text-to-video · Grok Imagine Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video motion. Required field. - Should be detailed and specific about the desired visual motion - Describe movement, action sequences, camera work, and timing - Include details about subjects, environments, and motion dynamics - Maximum length: 5000 characters - Supports English language prompts
`aspect_ratio`	string	Specifies the width-to-height ratio of the generated video. Controls the aspect ratio of the output. - 2:3: Portrait orientation (vertical) - 3:2: Landscape orientation (horizontal) - 1:1: Square format - 16:9: Wide screen format - 9:16: Tall screen format Default: 2:3 Allowed: `2:3`, `3:2`, `1:1`, `16:9`, `9:16`. Default: `2:3`.
`mode`	string	Specifies the generation mode affecting the style and intensity of motion. - fun: More creative and playful interpretation - normal: Balanced approach with good motion quality - spicy: More dynamic and intense motion effects Default: normal Allowed: `fun`, `normal`, `spicy`. Default: `normal`.
`duration`	number	The duration of the generated video (in seconds) (6-30). (Minimum: 6, Maximum: 30, Step: 1)
`resolution`	string	The resolution of the generated video. Allowed: `480p`, `720p`, `1080p`. Default: `480p`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/02-image-to-video-pro · Hailuo Pro Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video animation (Max length: 1500 characters)
`image_url` (required)	string	Input image to animate (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`end_image_url`	string	Optional URL of the image to use as the last frame of the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`prompt_optimizer`	boolean	Whether to use the model's prompt optimizer (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/02-image-to-video-standard · Hailuo Standard Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the video to generate (Max length: 1500 characters)
`image_url` (required)	string	The URL of the image to use as the first frame of the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`end_image_url`	string	Optional URL of the image to use as the last frame of the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`duration` (required)	string	Required. Video duration in seconds: 6 or 10. Allowed: `6`, `10`.
`resolution` (required)	string	Required. The resolution of the generated video. Allowed: `512P`, `768P`.
`prompt_optimizer`	boolean	Whether to use the model's prompt optimizer (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/02-text-to-video-pro · Hailuo Pro Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt for video generation (Max length: 1500 characters)
`prompt_optimizer`	boolean	Whether to use the model's prompt optimizer (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/02-text-to-video-standard · Hailuo Standard Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text description for video generation (Max length: 1500 characters)
`duration` (required)	string	Required. Video duration in seconds: 6 or 10. Allowed: `6`, `10`.
`prompt_optimizer`	boolean	Whether to use the model's prompt optimizer (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/2-3-image-to-video-pro · Hailuo 2.3 Pro Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video animation (Max length: 5000 characters)
`image_url` (required)	string	Input image to animate (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`duration` (required)	string	Required. The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution. Allowed: `6`, `10`.
`resolution` (required)	string	Required. The resolution of the generated video. Allowed: `768P`, `1080P`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

hailuo/2-3-image-to-video-standard · Hailuo 2.3 Standard Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video animation (Max length: 5000 characters)
`image_url` (required)	string	Input image to animate (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`duration` (required)	string	Required. The duration of the video in seconds. 10 seconds videos are not supported for 1080p resolution. Allowed: `6`, `10`.
`resolution` (required)	string	Required. The resolution of the generated video. Allowed: `768P`, `1080P`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

happyhorse-1-1/image-to-video · HappyHorse-1-1 image-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Describes the video content to generate. Supports any language. Maximum: 5,000 non-Chinese characters or 2,500 Chinese Default: .
`image_urls` (required)	array	The URL of the first frame image. Image constraints: 1. Formats: JPEG, JPG, PNG, WEBP. 2. Resolution: Width and height must both be at least 300 pixels. 3. Aspect ratio: Between 1:2.5 and 2.5:1. 4. File size: Up to 20 MB.
`resolution`	string	The resolution of the generated video. Options: 720p; 1080p The output keeps the aspect ratio of the input image; 720p / 1080p set the resolution tier. Allowed: `720p`, `1080p`. Default: `1080p`.
`duration`	number	The duration of the generated video, in seconds. The value must be an integer in the range [3, 15]. Default: 5 Default: `5`.

happyhorse-1-1/reference-to-video · HappyHorse-1-1 reference-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	A description of the desired elements and visual style for the generated video. Input in any language is supported. Up to 5,000 characters. Use "[Image 1]", "[Image 2]" to refer to the images in reference_image, in the same order. When using a reference, specify the object in the image, such as "the woman in a red qipao in [Image 1]".
`reference_image` (required)	array	The URL of a reference image. Image requirements: 1. Formats: JPEG, JPG, PNG, WEBP. 2. Resolution: The shortest side must be at least 400 pixels. A clear image with a resolution of 720P or higher is recommended. Avoid using images that are too small, blurry, or overly compressed, as this can degrade the output quality. 3. Maximum file size: 20 MB.
`resolution`	string	The resolution tier of the generated video. Options: 720p; 1080p Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	The aspect ratio of the generated video. Options: 16:9; 9:16; 3:4; 4:3; 4:5; 5:4; 1:1; 9:21; 21:9 Allowed: `16:9`, `9:16`, `3:4`, `4:3`, `4:5`, `5:4`, `1:1`, `9:21`, `21:9`. Default: `16:9`.
`duration`	number	The duration of the generated video, in seconds. Value range: An integer from 3 to 15. Default: `5`.

happyhorse-1-1/text-to-video · HappyHorse-1-1 text-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text description of the video to generate. Supports any language. Maximum 5,000 non-Chinese characters or 2,500 Chinese
`resolution`	string	Output video resolution. Options: 720p; 1080p Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	Output video aspect ratio. Options: 16:9; 9:16; 1:1; 4:3; 3:4; 4:5; 5:4; 9:21; 21:9 Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `4:5`, `5:4`, `9:21`, `21:9`. Default: `16:9`.
`duration`	number	Output video duration in seconds. Integer, 3–15. Default 5. Default: `5`.

happyhorse/image-to-video · happyhorse-image-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Text prompt describing the video to generate (any language). Up to 5,000 characters.
`image_urls` (required)	array	First-frame image URL list. Exactly one image is required. Image constraints: Format: JPEG, JPG, PNG, WEBP. Resolution: Width and height must be at least 300 pixels. Aspect ratio: 1:2.5 to 2.5:1. File size: Up to 10 MB.
`resolution`	string	Output video resolution: 720p or 1080p (default). The output keeps the aspect ratio of the input image; 720p / 1080p set the resolution tier. Allowed: `720p`, `1080p`. Default: `1080p`.
`duration`	integer	Output duration in seconds. Must be between 3 and 15. Defaults to 5. Default: `5`.
`seed`	integer	Random seed for reproducibility. Default: `0`.

happyhorse/reference-to-video · happyhorse/reference-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the video to generate (any language). Up to 5,000 characters.
`reference_image` (required)	array	Reference image URL list. Provide 1–9 images. The order defines which image is character1, character2, etc. Image limits: Format: JPEG, JPG, PNG, and WEBP. Resolution: shortest side at least 400 px. 720P or higher recommended. Avoid small, blurry, or heavily compressed images, as they degrade output quality. File size: 10 MB maximum.
`resolution`	string	Output video resolution: 720p or 1080p (default). Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	Output aspect ratio. Valid values: 16:9 (default), 9:16, 1:1, 4:3, 3:4. Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. Default: `16:9`.
`duration`	integer	Output duration in seconds (integer). Must be between 3 and 15. Defaults to 5. Default: `5`.
`seed`	integer	Random seed for reproducibility. Default: `0`.

happyhorse/text-to-video · happyhorse-text-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the video to generate (any language). Up to 5,000 characters.
`resolution`	string	Output video resolution: 720p or 1080p (default). Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	Output aspect ratio. Valid values: 16:9 (default), 9:16, 1:1, 4:3, 3:4. Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. Default: `16:9`.
`duration`	integer	Output duration in seconds (integer). Must be between 3 and 15. Defaults to 5. Default: `5`.
`seed`	integer	Random seed for reproducibility. Default: `0`.

happyhorse/video-edit · happyhorse/video-edit · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Required edit instruction describing the intended change (e.g., style transfer / local replacement). Up to 5,000 characters.
`video_url` (required)	string	URL of the input video (one video). Video requirements: Format: MP4, MOV (H.264 encoding recommended). Duration: 3–60 seconds. Resolution: the longer side must not exceed 2,160 px; the shorter side must be at least 320 px. Aspect ratio: 1:2.5–2.5:1. File size: up to 100 MB. Frame rate: greater than 8 fps.
`reference_image`	array	Optional reference image URL list (0–5). Image requirements: Format: JPEG, JPG, PNG, WEBP. Resolution: both width and height must be at least 300 px. Aspect ratio: 1:2.5–2.5:1. File size: up to 10 MB.
`resolution`	string	Output video resolution: 720p or 1080p (default). Allowed: `720p`, `1080p`. Default: `1080p`.
`audio_setting`	string	Audio handling: auto lets the model handle audio; origin keeps the input video's original audio where possible. Allowed: `auto`, `origin`. Default: `auto`.
`seed`	integer	Random seed for reproducibility. Default: `0`.

kling-2.6/image-to-video · Kling 2.6 Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt (max 2,500 characters).
`image_urls` (required)	array	Image URLs for video generation. (Uploaded file URLs, not file content; supported types: image/jpeg, image/png; maximum file size: 10.0MB)
`sound` (required)	boolean	Required. This parameter specifies whether the generated video contains sound (boolean: true/false)
`duration` (required)	string	Required. Video duration (unit: seconds) Allowed: `5`, `10`.

kling-2.6/motion-control · Kling 2.6 motion-control · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	A text description of the desired output. Maximum length is 2500 characters. (Max length: 2500 characters)
`input_urls` (required)	array	An array containing a single image URL. The photo must clearly show the subject's head, shoulders, and torso. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/jpg; Max size: 10.0MB,size needs to be greater than 300px, aspect ratio 2:5 to 5:2.)
`video_urls` (required)	array	An array containing a single video URL. The duration must be between 3 to 30 seconds, and the video must clearly show the subject's head, shoulders, and torso. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime; Max size: 100.0MB)
`character_orientation` (required)	string	Required. Generate the orientation of the characters in the video. 'image': same orientation as the person in the picture (max 10s video). 'video': consistent with the orientation of the characters in the video (max 30s video). Allowed: `image`, `video`.
`mode` (required)	string	Required. Output resolution: "720p" or "1080p". Allowed: `720p`, `1080p`.

kling-2.6/text-to-video · Kling 2.6 Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt (max 2,500 characters).
`sound` (required)	boolean	Required. This parameter specifies whether the generated video contains sound (boolean: true/false)
`aspect_ratio` (required)	string	Required. This parameter defines the video aspect ratio Allowed: `1:1`, `16:9`, `9:16`.
`duration` (required)	string	Required. Video duration (unit: seconds) Allowed: `5`, `10`.

kling-3.0-omni/image-to-video · Kling 3.0 Omni Image To Video · POST /v1/videos/generations

No input fields beyond the prompt.

kling-3.0-omni/reference-to-video · Kling 3.0 Omni Reference To Video · POST /v1/videos/generations

No input fields beyond the prompt.

kling-3.0-omni/text-to-video · Kling 3.0 Omni Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text description of the video. It must not be empty after leading and trailing whitespace is removed, and must not exceed 3,072 characters.
`customize_multi_shots`	boolean	Optional, default false. Set true for custom multi-shot (multi_prompt required). Default: `false`.
`prefer_multi_shots`	boolean	Whether to enable intelligent shot planning. This field is mutually exclusive with `customize_multi_shots`. Both fields may be `false`, but they cannot both be `true`.
`multi_prompt`	array	List of custom shots. When `customize_multi_shots` is `true`, this field is required, must not be empty, and supports up to 6 shots. When `customize_multi_shots` is `false`, it must be an empty array or omitted.
`elements`	array	List of one-time subject assets. The default is an empty array. When using only multi-image subjects, up to 7 subjects can be uploaded. When using only video character subjects, the number of video character subjects must not exceed 3. When using both video character and multi-image subjects, the number of video character subjects must not exceed 3, and the number of multi-image subjects must not
`audio`	boolean	Whether to add audio to the generated video. `true` enables audio; `false` disables audio. Default: `false`.
`resolution`	string	Resolution of the generated video. Available values are `720p` (outputs a 720p video), `1080p` (outputs a 1080p video), and `4k` (outputs a 4K video). Allowed: `720p`, `1080p`, `4k`. Default: `720p`.
`aspect_ratio`	string	Aspect ratio of the generated video. Supported values are `16:9`, `9:16`, and `1:1`. Allowed: `16:9`, `9:16`, `1:1`. Default: `16:9`.
`duration`	integer	Total video duration in seconds. The supported range is 3 to 15 seconds, and the default is 5 seconds. Allowed: `3`, `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`. Default: `5`.

kling-3.0-omni/transformation · Kling 3.0 Omni Transformation · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Video description. It must not be empty after leading and trailing whitespace is removed. Maximum length: 3,072 characters.
`video_urls`	array	Array of video URLs. Exactly 1 video is required. HTTP, HTTPS, and OSS URLs are supported. Videos must be in MP4 or MOV format; each file must not exceed 200 MB; duration must be between 3 and 15.5 seconds; width and height must each be between 700 and 4,553 px; total pixels must not exceed 8,294,400; the aspect ratio must be between 0.4 and 2; and the frame rate must be between 24 and 60 fps.
`image_urls`	array	Array of image URLs. The maximum number of images depends on the number and types of reference subjects. When using only multi-image subjects, the combined number of reference images and multi-image subjects must not exceed 4. Video character subjects cannot be used together with multi-image subjects or reference images. HTTP, HTTPS, and OSS URLs are supported. Images must be in JPG, JPEG, or PNG
`duration`	string	Video duration. This field may be configured when using a video with images.
`resolution`	string	Video resolution. `720p` outputs a 720p video, `1080p` outputs a 1080p video, and `4k` outputs a 4K video. Allowed: `720p`, `1080p`, `4k`. Default: `720p`.
`aspect_ratio`	string	Video aspect ratio. Only `auto` can be used with video-only input. When using a video with images, `16:9`, `9:16`, and `1:1` are supported; `auto` is not supported. Allowed: `16:9`, `9:16`, `1:1`, `auto`. Default: `16:9`.
`audio`	boolean	No audio is generated when a video is provided; set false. Allowed: `false`, `true`.
`elements`	array	List of one-time subject assets. The default is an empty array. When using only multi-image subjects, up to 7 subjects can be uploaded. When using only video character subjects, the number of video character subjects must not exceed 3. When using both video character and multi-image subjects, the number of video character subjects must not exceed 3, and the number of multi-image subjects must not

kling-3.0/motion-control · Kling-3.0 motion-control · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	(Optional) Text prompt words, used to guide the generation of animation content. Can be empty or 0 - 2500 characters long.
`input_urls` (required)	array	(Required) Include a URL of an image
`video_urls` (required)	array	(Required) Include a video URL
`mode`	string	Optional. Output resolution: "720p" (default) or "1080p". Allowed: `720p`, `1080p`. Default: `720p`.
`character_orientation`	string	(Optional) Reference source for character orientation. video: Refer to video (recommended); image: Refer to image. Default value: video

kling-3.0/video · Kling 3.0 · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Required when multi_shots is false. Up to 2,500 characters.
`image_urls`	array	First and last frame image URLs. Optional; not required when using kling_elements. When multi_shots is false: if length is 2, index 0 is the first frame and index 1 is the last frame; if length is 1, the array item serves as the first frame. When multi_shots is true: only the first frame is supported.
`sound` (required)	boolean	Required. Whether to generate audio (speech, sound effects, ambience) with the video. Affects price.
`duration` (required)	string	Required. Video duration in seconds, 3–15 (string, e.g. "5"). In multi-shot mode, output length and billing follow the sum of multi_prompt[].duration (3–15 s); set duration to the same total. Allowed: `3`, `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`.
`aspect_ratio`	string	Optional when image_urls is provided (the output follows the first frame's aspect ratio). For text-to-video, set it explicitly: 16:9, 9:16 or 1:1. Allowed: `16:9`, `9:16`, `1:1`.
`mode` (required)	string	Required. Generation mode. std has standard resolution, pro has higher resolution, 4K has 4K resolution. Resolution mapping: - std mode: 16:9 (1280×720), 9:16 (720×1280), 1:1 (720×720) - pro mode: 16:9 (1920×1080), 9:16 (1080×1920), 1:1 (1080×1080) - 4K mode: 16:9 (3840×2160), 9:16 (2160×3840), 1:1 (2160×2160) Allowed: `std`, `pro`, `4K`.
`multi_shots` (required)	boolean	Required. Whether to use multi-shot mode. true enables multi-shot mode, false enables single-shot mode.
`multi_prompt`	array	Shot prompts. Takes effect when multi_shots is true. Used to describe the text and duration of each shot. Supports up to 5 shots. Each shot duration is 1-12 seconds. If you need to use elements, add them after the prompt.
`kling_elements`	array	Referenced elements. Detailed information about elements referenced in the prompt. A single task can reference a maximum of three elements.

kling/v2-1-master-image-to-video · Kling V2.1 Master Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the video to generate (Max length: 5000 characters)
`image_url` (required)	string	URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`negative_prompt`	string	Negative prompt to exclude certain elements from the video (Max length: 500 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.

kling/v2-1-master-text-to-video · Kling V2.1 Master Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the video you want to generate (Max length: 5000 characters)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`aspect_ratio`	string	The aspect ratio of the generated video frame Allowed: `16:9`, `9:16`, `1:1`. Default: `16:9`.
`negative_prompt`	string	Elements to avoid in the generated video (Max length: 500 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.

kling/v2-1-pro · Kling V2.1 Pro · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the video to generate (Max length: 5000 characters)
`image_url` (required)	string	URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`negative_prompt`	string	Terms to avoid in the generated video (Max length: 500 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.
`tail_image_url`	string	URL of the image to be used for the end of the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)

kling/v2-1-standard · Kling V2.1 Standard · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video content (Max length: 5000 characters)
`image_url` (required)	string	URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`negative_prompt`	string	Description of elements to avoid in the generated video (Max length: 500 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.

kling/v2-5-turbo-image-to-video-pro · Kling - V2.5 Turbo Image to Video Pro · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the video to generate (Max length: 2500 characters)
`image_url` (required)	string	URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`tail_image_url`	string	Tail frame image of video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`negative_prompt`	string	Negative prompt to exclude certain elements from the video (Max length: 2,496 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.

kling/v2-5-turbo-text-to-video-pro · Kling - V2.5 Turbo Text to Video Pro · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text description of the video you want to generate (Max length: 2500 characters)
`duration` (required)	string	Required. "5" or "10" (seconds). Allowed: `5`, `10`.
`aspect_ratio`	string	The aspect ratio of the generated video frame Allowed: `16:9`, `9:16`, `1:1`. Default: `16:9`.
`negative_prompt`	string	Things to avoid in the generated video (Max length: 2500 characters)
`cfg_scale`	number	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1) Default: `0.5`.

kling/v3-turbo-image-to-video · Kling - V3 Turbo Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the video to generate (Max length: 2500 characters)
`image_urls` (required)	array	Required. URL of the image to be used for the video (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`duration` (required)	string	Required. The duration of the generated video in seconds Optional duration: 3s - 15s
`resolution` (required)	string	Required. Resolution of the generated video (720p or 1080p) Allowed: `720p`, `1080p`.

kling/v3-turbo-text-to-video · Kling - V3 Turbo Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text description of the video you want to generate (Max length: 2500 characters)
`duration` (required)	string	Required. The duration of the generated video in seconds Optional duration: 3s - 15s
`aspect_ratio` (required)	string	Required. The aspect ratio of the generated video frame Allowed: `1:1`, `9:16`, `16:9`.
`resolution` (required)	string	Required. Resolution of the generated video (720p or 1080p) Allowed: `720p`, `1080p`.

minimax-h3/image-to-video · MiniMax H3 Image-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Video generation prompt, length is between 1 and 7000 characters.
`first_frame_url`	string	First frame image URL. Note: Either first_frame_url or last_frame_url must be provided. Publicly accessible HTTP(S) URL; supports JPG, JPEG, PNG, WEBP, HEIC, HEIF formats; single image size not exceeding 30 MB, image side length between 256 and 5760 pixels, aspect ratio between 0.4 and 2.5.
`last_frame_url`	string	Last frame image URL. Note: Either first_frame_url or last_frame_url must be provided. Image restrictions are the same as first_frame_url.
`duration` (required)	integer	Generated video duration, supporting integer values from 4 to 15 seconds. Allowed: `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`. Default: `6`.
`resolution`	string	Video resolution. Allowed: `768P`, `2K`. Default: `2K`.

minimax-h3/reference-to-video · MiniMax H3 Reference-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Video generation prompt, length is between 1 and 7000 characters.
`reference_image_urls`	array	Array of reference image URLs. Supports up to 9 images. Publicly accessible HTTP(S) URL; supported image formats include JPG, JPEG, PNG, WEBP, HEIC, and HEIF; a single image size cannot exceed 30 MB; the side length of the image must be between 256 and 5760 pixels, and the aspect ratio must be between 0.4 and 2.5. Provide at least one of reference_image_urls or reference_video_urls.
`reference_video_urls`	array	Array of reference video URLs. Supports up to 3 videos. Supports MP4, MOV; video encoding supports H.264, H.265; a single file size cannot exceed 50 MB; the duration of a single segment is 2 to 15 seconds, and the total duration of all reference videos cannot exceed 15 seconds; the video side length must be between 256 and 5760 pixels, the aspect ratio must be between 0.4 and 2.5, and the frame ra
`reference_audio_urls`	array	Array of reference audio URLs. Supports up to 3 audios. Supports WAV, MP3; a single file size cannot exceed 15 MB; the duration of a single segment is 2 to 15 seconds, and the total duration of all reference audios cannot exceed 15 seconds. reference_audio cannot be used alone, it must be accompanied by reference_image or reference_video.
`aspect_ratio`	string	Video aspect ratio. The default is adaptive, or a specific ratio can be specified. Allowed: `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`. Default: `adaptive`.
`duration` (required)	integer	The duration of the generated video, supporting integer values from 4 to 15 seconds. Allowed: `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`. Default: `6`.
`resolution`	string	Video resolution. Allowed: `768P`, `2K`. Default: `2K`.

minimax-h3/text-to-video · MiniMax H3 Text-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Video generation prompt, length is between 1 and 7000 characters.
`aspect_ratio` (required)	string	Video aspect ratio. Required for text-to-video, adaptive is not supported. Allowed: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`.
`duration` (required)	integer	Generated video duration, supports integer values from 4 to 15 seconds. Allowed: `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15`. Default: `6`.
`resolution`	string	Video resolution. Allowed: `768P`, `2K`. Default: `2K`.

omnihuman-1-5/human-identification · Omnihuman 1.5 Human Identification · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	Portrait image URL. Requirements: JPG/PNG/JPEG format, less than 5MB, resolution under 4096x4096. Recommended: single person facing forward, with the face occupying a large proportion of the image. Accepted file types: image/jpeg, image/png, image/jpg. Max file size: 5MB.

omnihuman-1-5/subject-detection · OmniHuman 1.5 Subject Detection · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	Portrait image URL. Supports detection of up to 5 subjects in the image. Accepted file types: image/jpeg, image/png, image/jpg. Max file size: 5MB.

pixverse-v6/extend · PixVerse V6 Video Extension · POST /v1/videos/generations

No input fields beyond the prompt.

pixverse-v6/image-to-video · PixVerse V6 Image-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Generate prompt, cannot be empty, length is limited to 3-5000 characters.
`image_urls` (required)	array	Without template_id, provide 1 image (used as the first frame). With template_id, provide the number of images given by the template's effect_type (1 or 2). Single image size not exceeding 20 MB. Supports HTTP, HTTPS, and OSS addresses. Supported image formats include JPG, JPEG, PNG, and WebP.
`quality` (required)	string	Required. Output video resolution. Supports 360p, 540p, 720p, and 1080p. Allowed: `360p`, `540p`, `720p`, `1080p`.
`duration` (required)	integer	Generated video duration in seconds, ranging from 1 to 15. Required when template_id is not passed; if template_id is passed, the video duration is fixed by the selected template, please do not pass this parameter at the same time.
`generate_audio_switch`	boolean	Whether to generate audio synchronized with the video content. Default: `false`.
`generate_multi_clip_switch`	boolean	Whether to generate a multi-clip video. Default: `false`.
`seed`	integer	Random seed, value range is 0-2147483647. Using the same parameters and seed helps improve result reproducibility.
`template_id`	string	Used to select a PixVerse video effect template. Please pass in the corresponding template_id. Once a template_id is provided, the video duration is fixed by the selected template, so duration cannot be set at the same time. effect_type indicates the number of images required by the selected template. Please upload the specified number of images accordingly. To preview the template effect, open .m

pixverse-v6/reference-to-video · PixVerse V6 Fusion / Reference-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Generate prompt, cannot be empty, length is limited to 3-5000 characters.
`image_references` (required)	array	Fusion multi-reference image list. `ref_name` must be unique within the same list. You can reference the reference object in the prompt via `@ref_name`.
`aspect_ratio` (required)	string	Required. Output video aspect ratio. Supported in text-to-video and Fusion multi-reference image to video modes. Allowed: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Output video resolution. Supports 360p, 540p, 720p, and 1080p. Allowed: `360p`, `540p`, `720p`, `1080p`.
`duration` (required)	integer	Required. Output video duration in seconds, 1–15.
`generate_audio_switch`	boolean	Whether to generate audio synchronized with the video content. Default: `false`.
`seed`	integer	Random seed, value range is 0-2147483647. Using the same parameters and seed helps improve the reproducibility of the results.

pixverse-v6/text-to-video · PixVerse V6 Text-to-Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Generate prompt, cannot be empty, length is limited to 3-5000 characters.
`aspect_ratio` (required)	string	Required. Output video aspect ratio. This parameter is supported in text-to-video and Fusion multi-reference image-to-video modes. Allowed: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, `2:3`, `3:2`, `21:9`.
`quality` (required)	string	Required. Output video resolution. Supports 360p, 540p, 720p, and 1080p. Allowed: `360p`, `540p`, `720p`, `1080p`.
`duration` (required)	integer	Required. Output video duration in seconds. PixVerse V6 supports 1–15 seconds.
`generate_audio_switch`	boolean	Whether to generate audio synchronized with the video content. Default: `false`.
`generate_multi_clip_switch`	boolean	Whether to generate a multi-clip video. Default: `false`.
`seed`	integer	Random seed, value range is 0–2147483647. Using the same parameters and seed helps improve result reproducibility.

pixverse-v6/transition · PixVerse V6 First & Last Frame Transition · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Generate prompt, cannot be empty, length is limited to 3-5000 characters.
`first_frame_image_url` (required)	string	First frame image URL. Supports HTTP, HTTPS, and OSS addresses; supported image formats include JPG, JPEG, PNG, and WebP; the size of a single image file must not exceed 20 MB
`last_frame_image_url` (required)	string	Last frame image URL. Supports HTTP, HTTPS, and OSS addresses; supported image formats include JPG, JPEG, PNG, and WebP; the size of a single image file must not exceed 20 MB
`quality` (required)	string	Required. Output video resolution. Supports 360p, 540p, 720p, and 1080p. Allowed: `360p`, `540p`, `720p`, `1080p`.
`duration` (required)	integer	Required. Output video duration in seconds. PixVerse V6 supports 1–15 seconds.
`generate_audio_switch`	boolean	Whether to generate audio synchronized with the video content. Default: `false`.
`seed`	integer	Random seed, value range is 0–2147483647. Using the same parameters and seed helps improve result reproducibility.

runway/gen4-aleph · Generate Aleph Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Describes how to transform the input video.
`video_url` (required)	string	Reference video URL to base the video-to-video generation on. The AI will transform and enhance this video according to the prompt.
`watermark`	string	Optional watermark text content. An empty string indicates no watermark, while a non-empty string will display the specified text as a watermark in the video.
`upload_cn`	boolean	Optional. Defaults to false. Default: `false`.
`aspect_ratio`	string	Video aspect ratio. Allowed: `16:9`, `9:16`, `4:3`, `3:4`, `1:1`, `21:9`.
`seed`	integer	Random seed. Set for reproducible generation.
`reference_image`	string	Reference image URL to influence the style or content of the output.

runway/gen4-extend · Extend AI Video · POST /v1/videos/generations

Field	Type	Details
`task_id` (required)	string	Unique identifier of the original video generation task. Must be a valid task ID from a previously generated video.
`prompt` (required)	string	Descriptive text that guides the continuation of the video. Explain what actions, movements, or developments should happen next. Be specific but maintain consistency with the original video content.
`quality` (required)	string	Video resolution, optional values are 720p or 1080p.
`watermark`	string	Video watermark text content. An empty string indicates no watermark, while a non-empty string will display the specified text as a watermark in the bottom right corner of the video.

runway/gen4-video · Generate AI Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Descriptive text that guides the AI video generation. Be specific about subject, action, style, and setting. When used with an image, describes how to animate or modify the image content. Maximum length is 1800 characters.
`image_url`	string	Optional reference image URL to base the video on. When provided, the AI will create a video animating or extending this image.
`duration` (required)	number	Video duration, optional values are 5 or 10. If 10-second video is selected, 1080p resolution cannot be used
`quality` (required)	string	Video resolution, optional values are 720p or 1080p. If 1080p is selected, 10-second video cannot be generated
`aspect_ratio`	string	Video aspect ratio parameter. Required parameter for text-to-video generation requests. This parameter is invalid when image_url is passed, and the aspect ratio will ultimately be determined by the provided image. Allowed: `16:9`, `4:3`, `1:1`, `3:4`, `9:16`.
`watermark`	string	Video watermark text content. An empty string indicates no watermark, while a non-empty string will display the specified text as a watermark in the bottom right corner of the video.

veo-3.1 · Generate Veo3.1 Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt describing the desired video content. Required for all generation modes. - Should be detailed and specific in describing video content - Can include actions, scenes, style and other information - For image-to-video, describe how you want the image to come alive
`model`	string	Veo 3.1 tier: "veo3_fast" (default), "veo3_lite" or "veo3" (Quality). The top-level model stays "veo-3.1". REFERENCE_2_VIDEO supports veo3_fast and veo3_lite. Allowed: `veo3_fast`, `veo3_lite`, `veo3`. Default: `veo3_fast`.
`image_urls`	array	Image URLs. FIRST_AND_LAST_FRAMES_2_VIDEO: 1 image (first frame) or 2 images (first + last frame). REFERENCE_2_VIDEO: 1–3 reference images, 8-second duration only.
`generation_type`	string	Video generation mode (optional). Specifies different video generation approaches: - TEXT_2_VIDEO: Text-to-video - Generate videos using only text prompts - FIRST_AND_LAST_FRAMES_2_VIDEO: First and last frames to video - Flexible image-to-video generation mode - 1 image: Generate video based on the provided image - 2 images: First image as first frame, second image as last frame, generatin Allowed: `TEXT_2_VIDEO`, `FIRST_AND_LAST_FRAMES_2_VIDEO`, `REFERENCE_2_VIDEO`.
`aspect_ratio`	string	Video aspect ratio. Specifies the dimension ratio of the generated video. Available options: - 16:9: Landscape video format. - 9:16: Portrait video format, suitable for mobile short videos - Auto: In auto mode, the video will be automatically center-cropped based on whether your uploaded image is closer to 16:9 or 9:16. Default value is 16:9. Allowed: `16:9`, `9:16`, `Auto`. Default: `16:9`.
`enable_fallback`	boolean	Deprecated. Remove it from requests. Default: `false`.
`enable_translation`	boolean	Optional. When true, the prompt is translated to English before generation.
`watermark`	string	Watermark text. - Optional parameter - If provided, a watermark will be added to the generated video
`resolution`	string	Output resolution: 720p (default), 1080p or 4k. For 1080p and 4k, the video URL is in resultJson.data.result_urls (the 720p version is in data.origin_urls). Controls the pixel dimensions of the generated video. Higher resolution results in greater clarity and detail, while lower resolution allows for faster generation. Allowed: `720p`, `1080p`, `4k`. Default: `720p`.
`duration`	integer	The duration of the generated video, in seconds. Optional values are 4, 6, 8. Important Note: - The REFERENCE_2_VIDEO mode currently only supports a duration of 8 seconds. Allowed: `4`, `6`, `8`. Default: `8`.

veo/extend · Extend Veo3.1 Video · POST /v1/videos/generations

Field	Type	Details
`task_id` (required)	string	The task ID of the original video generation. Must be a valid task ID returned by the video generation API.
`prompt` (required)	string	A text prompt describing the content of the extended video. It should detail how you want the video to be extended, including actions, scene changes, styles, etc.
`seeds`	integer	A random seed parameter that controls the randomness of the generated content. Range: 10000-99999. The same seed will generate similar video content, while different seeds will generate different video content. If not specified, the system will automatically assign a random seed.
`model`	string	Extension tier: "fast" (default), "quality" or "lite". Billed per extension at the chosen tier. Allowed: `fast`, `quality`, `lite`. Default: `fast`.
`watermark`	string	Watermark text (optional). If provided, a watermark will be added to the generated video.

veo/get-1080p-video · Get 1080P Video · POST /v1/generations

Field	Type	Details
`taskId` (required)	string	taskId
`index`	string	video index

veo/get-4k-video · Get 4K Video · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID
`index`	integer	video index Default: `0`.

vidu-q4/image-to-video · Vidu Q4 Image To Video · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Text description of the motion and scene. Optional. Up to 20,000 characters.
`duration`	integer	Video length in seconds. Integer from 3 to 16. Default: `5`.
`resolution`	string	Output resolution. Allowed: `540p`, `720p`, `1080p`, `2k`, `4k`. Default: `720p`.
`audio`	boolean	Generate synchronized audio (dialogue and sound effects). Set false for a silent video. Default: `true`.
`image_url` (required)	string	First-frame image URL (http/https). JPG, JPEG, PNG or WEBP, up to 50 MB. The video inherits this image's aspect ratio.

vidu-q4/reference-to-video · Vidu Q4 Reference To Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text description of the video. Refer to inputs by order, e.g. "the man in reference image 2 says ... using reference audio 1". Up to 20,000 characters.
`duration`	integer	Video length in seconds. Integer from 3 to 16. Default: `5`.
`resolution`	string	Output resolution. Allowed: `540p`, `720p`, `1080p`, `2k`, `4k`. Default: `720p`.
`audio`	boolean	Generate synchronized audio (dialogue and sound effects). Set false for a silent video. Default: `true`.
`reference_image_urls` (required)	array	Reference image URLs (http/https), 1 to 15. JPG, JPEG, PNG or WEBP.
`reference_audio_urls`	array	Optional reference audio URLs (http/https), up to 3. MP3 only, each 3-12 seconds and up to 50 MB.
`aspect_ratio`	string	Output aspect ratio. Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. Default: `16:9`.

wan/2-2-a14b-image-to-video-turbo · Wan - 2.2 A14B Image to Video Turbo · POST /v1/videos/generations

Field	Type	Details
`image_url` (required)	string	URL of the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`prompt` (required)	string	The text prompt to guide video generation. (Max length: 5000 characters)
`resolution`	string	Resolution of the generated video (480p or 720p). Default value: "720p" Allowed: `480p`, `720p`. Default: `720p`.
`enable_prompt_expansion`	boolean	Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. (Boolean value (true/false))
`seed`	number	Optional. Omit for a random seed.
`acceleration`	string	Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'none'. Default value: "none" Allowed: `none`, `regular`. Default: `none`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-2-a14b-text-to-video-turbo · Wan - 2.2 A14B Text to Video Turbo · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt to guide video generation. (Max length: 5000 characters)
`resolution`	string	Resolution of the generated video (480p or 720p). Default value: "720p" Allowed: `480p`, `720p`. Default: `720p`.
`aspect_ratio`	string	Aspect ratio of the generated video (16:9 or 9:16). Default value: "16:9" Allowed: `16:9`, `9:16`. Default: `16:9`.
`enable_prompt_expansion`	boolean	Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. (Boolean value (true/false))
`seed`	number	Optional. Omit for a random seed.
`acceleration`	string	Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'none'. Default value: "none" Allowed: `none`, `regular`. Default: `none`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-5-image-to-video · Wan 2.5 - Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt describing the desired video motion. Maximum length: 800 characters.
`image_url` (required)	string	URL of the image to use as the first frame. Must be publicly accessible. - Please provide the URL of the uploaded file, not raw file content - Accepted types: `image/jpeg`, `image/png`, `image/webp` - Max size: 10.0MB
`duration` (required)	string	The duration of the generated video in seconds. - `5`: 5 seconds - `10`: 10 seconds Allowed: `5`, `10`.
`resolution` (required)	string	Required. 720p or 1080p. Allowed: `720p`, `1080p`.
`negative_prompt`	string	Negative prompt used to describe content to avoid. Maximum length: 500 characters.
`enable_prompt_expansion`	boolean	Whether to enable prompt rewriting using LLM. - Boolean value: `true` / `false`
`seed`	integer	Random seed for reproducibility. If omitted, a random seed is chosen.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-5-text-to-video · Wan 2.5 - Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	The text prompt for video generation. Supports Chinese and English. Maximum length: 800 characters.
`duration` (required)	string	The duration of the generated video in seconds. - `5`: 5 seconds - `10`: 10 seconds Allowed: `5`, `10`.
`aspect_ratio`	string	The aspect ratio of the generated video. - `16:9`: Landscape - `9:16`: Portrait - `1:1`: Square Allowed: `16:9`, `9:16`, `1:1`.
`resolution` (required)	string	Required. 720p or 1080p. Allowed: `720p`, `1080p`.
`negative_prompt`	string	Negative prompt used to describe content to avoid. Maximum length: 500 characters.
`enable_prompt_expansion`	boolean	Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. - Boolean value: `true` / `false`
`seed`	integer	Random seed for reproducibility. If omitted, a random seed is chosen.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-6-flash-image-to-video · Wan - 2.6-flash-image-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompts for video generation. Supports Chinese and English, 2–1,500 characters.
`image_urls` (required)	array	A list of image URLs. All images must be at least 256x256px. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`duration`	string	The duration of the generated video in seconds Allowed: `5`, `10`, `15`. Default: `5`.
`resolution`	string	Video resolution tier Allowed: `720p`, `1080p`. Default: `1080p`.
`audio` (required)	boolean	Whether to generate video with audio. Audio directly affects the cost, as the pricing differs between videos with sound and silent videos. (Boolean value (true/false))
`multi_shots`	boolean	The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-6-flash-video-to-video · Wan - 2-6-flash-video-to-video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompts for video generation. Supports Chinese and English, 2–1,500 characters.
`video_urls` (required)	array	Reference video URLs. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 10.0MB)
`duration`	string	The duration of the generated video in seconds Allowed: `5`, `10`. Default: `5`.
`resolution`	string	Video resolution tier Allowed: `720p`, `1080p`. Default: `1080p`.
`audio`	boolean	Whether to generate video with audio. Audio directly affects the cost, as the pricing differs between videos with sound and silent videos. (Boolean value (true/false))
`multi_shots`	boolean	The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions. (Boolean value (true/false))
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-6-image-to-video · Wan 2.6 - Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompts for video generation. Supports both Chinese and English, with a minimum of 2 characters and a maximum of 5,000 characters. (Max length: 5000 characters)
`image_urls` (required)	array	Upload an image file to use as input for the API (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB),All images must be at least 256x256px.
`duration`	string	The duration of the generated video in seconds Allowed: `5`, `10`, `15`. Default: `5`.
`resolution`	string	Video resolution tier Allowed: `720p`, `1080p`. Default: `1080p`.
`multi_shots`	boolean	The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions. Default: `false`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-6-text-to-video · Wan 2.6 - Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompts for video generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters. (Max length: 5000 characters)
`duration`	string	The duration of the generated video in seconds Allowed: `5`, `10`, `15`. Default: `5`.
`resolution`	string	Output resolution: 720p or 1080p. Set this field explicitly. Allowed: `720p`, `1080p`.
`multi_shots`	boolean	The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions. Default: `false`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-6-video-to-video · Wan 2.6 - Video to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompts for video generation. Supports both Chinese and English, with a minimum of 2 characters and a maximum of 5,000 characters. (Max length: 5000 characters)
`video_urls` (required)	array	Reference video URLs. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 10.0MB)
`duration`	string	The duration of the generated video in seconds Allowed: `5`, `10`. Default: `5`.
`resolution`	string	Output resolution: 720p or 1080p. Set this field explicitly. Allowed: `720p`, `1080p`.
`multi_shots`	boolean	The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions. Default: `false`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-image-to-video · Wan 2.7 - Image to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Positive prompt. Maximum length: 5000 characters.
`negative_prompt`	string	Negative prompt. Maximum length: 500 characters.
`first_frame_url`	string	First frame image URL.
`last_frame_url`	string	Last frame image URL.
`first_clip_url`	string	First clip video URL, used for video continuation.
`driving_audio_url`	string	Driving audio URL.
`resolution`	string	Video resolution. - `720p`: 720p - `1080p`: 1080p Allowed: `720p`, `1080p`. Default: `1080p`.
`duration`	integer	Total output video duration in seconds. - Minimum: `2` - Maximum: `15` - Default: `5` Default: `5`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default value: `true`. Default: `true`.
`watermark`	boolean	Whether to add an AI-generated watermark. Default value: `false`. Default: `false`.
`seed`	integer	Random seed. - Minimum: `0` - Maximum: `2147483647`
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-r2v · Wan 2.7 - Reference to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Text prompt. Required. Describes the desired elements and visual features in the generated video. Supports Chinese and English. Maximum length: 5000 characters.
`negative_prompt`	string	Optional negative prompt describing what should not appear in the video. Supports Chinese and English. Maximum length: 500 characters.
`reference_image`	array	Array of reference image URLs. At least one of `reference_image` or `reference_video` must be provided. The total number of images and videos cannot exceed 5.
`reference_video`	array	Array of reference video URLs. At least one of `reference_image` or `reference_video` must be provided. The total number of images and videos cannot exceed 5.
`first_frame`	string	First frame image URL. At most one image can be provided. If supplied, `aspect_ratio` is ignored and the output uses a ratio close to the first frame image.
`reference_voice`	string	Audio URL used to specify the voice timbre of the subject in the reference material. Rules: - If `reference_video` contains audio and `reference_voice` is not provided, the original video audio is used by default - If both `reference_video` and `reference_voice` are provided, `reference_voice` takes priority Audio limits: - Formats: `wav`, `mp3` - Duration: `1` to `10` seconds - File size: up to `
`resolution`	string	Output video resolution tier. Available values: `720p`, `1080p`. Default value: `1080p`. Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	Output video aspect ratio. Effective logic: - If `first_frame` is not provided: the video is generated using the specified `aspect_ratio` - If `first_frame` is provided: `aspect_ratio` is ignored and the output uses a ratio close to the first frame image Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. Default: `16:9`.
`duration`	integer	Output video duration in seconds. Valid range is an integer from `2` to `10`. Default value: `5`. Default: `5`.
`prompt_extend`	boolean	Whether to enable prompt rewriting. When enabled, the model expands the input prompt. This usually works better for short prompts but increases processing time. Default: `true`.
`watermark`	boolean	Whether to add a watermark. The watermark is placed in the lower-right corner of the video with the fixed text "AI generated". Default: `false`.
`seed`	integer	Random seed. Range: `0-2147483647`. If omitted, the system generates one automatically.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-text-to-video · Wan 2.7 - Text to Video · POST /v1/videos/generations

Field	Type	Details
`prompt` (required)	string	Positive prompt. Minimum length: 1 character. Maximum length: 5000 characters.
`negative_prompt`	string	Negative prompt. Maximum length: 500 characters.
`audio_url`	string	Optional custom audio URL.
`resolution`	string	Video resolution. - `720p`: 720p - `1080p`: 1080p Allowed: `720p`, `1080p`. Default: `1080p`.
`ratio`	string	Video aspect ratio. - `16:9`: Landscape - `9:16`: Portrait - `1:1`: Square - `4:3`: Landscape 4:3 - `3:4`: Portrait 3:4 Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. Default: `16:9`.
`duration`	integer	Video duration in seconds. - Minimum: `2` - Maximum: `15` - Default: `5` Default: `5`.
`prompt_extend`	boolean	Whether to enable intelligent prompt rewriting. Default value: `true`. Default: `true`.
`watermark`	boolean	Whether to add an AI-generated watermark. Default value: `false`. Default: `false`.
`seed`	integer	Random seed. - Minimum: `0` - Maximum: `2147483647`
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-7-videoedit · Wan 2.7 - Video Edit · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Optional text prompt describing the expected elements and visual features in the generated video. Supports Chinese and English. Maximum length: 5000 characters.
`negative_prompt`	string	Optional negative prompt describing content that should not appear in the video. Supports Chinese and English. Maximum length: 500 characters.
`video_url` (required)	string	URL of the source video to edit. Required. Only one video is supported. - Formats: `mp4`, `mov` - Duration: `2` to `10` seconds - Resolution: width and height range `[240,4096]` pixels - Aspect ratio: `1:8` to `8:1` - File size: up to `100MB` - Supports public `http/https` URLs or temporary `oss` URLs
`reference_image`	string	Optional reference image URL for character, clothing, or style guidance. - Formats: `JPEG`, `JPG`, `PNG` (no alpha channel), `WEBP` - Resolution: width and height range `[240,8000]` pixels - Aspect ratio: `1:8` to `8:1` - Supports public `http/https` URLs or temporary `oss` URLs
`resolution`	string	Output video resolution tier. `1080p` costs more than `720p`. Default value: `1080p`. - `720p`: 720p - `1080p`: 1080p Allowed: `720p`, `1080p`. Default: `1080p`.
`aspect_ratio`	string	Output video aspect ratio. - If omitted: the output uses an aspect ratio close to the input video - If provided: the output uses the specified aspect ratio - Available values: `16:9`, `9:16`, `1:1`, `4:3`, `3:4` Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`.
`duration`	integer	Output video duration in seconds. - Default `0` means using the full input video duration without truncation - If a value is provided, the output is clipped from second `0` to the specified length - Valid values are `0` or any integer in `[2,10]` Default: `0`.
`audio_setting`	string	Video audio setting. - `auto`: default, the model decides whether to regenerate audio based on the `prompt` - `origin`: force keeping the original input video audio Allowed: `auto`, `origin`. Default: `auto`.
`prompt_extend`	boolean	Whether to enable prompt rewriting. When enabled, the model expands the input prompt. This usually works better for short prompts but increases processing time. Default: `true`.
`watermark`	boolean	Whether to add a watermark. The watermark is placed in the lower-right corner of the video with the fixed text "AI generated". Default: `false`.
`seed`	integer	Random seed. Range: `0-2147483647`. If omitted, the system generates one automatically.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/3-0-video · Wan 3.0 - Video · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Text prompt, supporting both Chinese and English. Up to 20,000 characters. Required for text-to-video generation; for other modes, it is recommended to provide it together with media. In reference mode, use Image1/Video1/Audio1 to reference the provided media.
`first_frame_url`	string	URL of the first-frame image. Up to 1 image, used strictly as the first frame of the video. Used for first-frame-to-video / first-and-last-frame-to-video generation. Cannot be provided together with `reference_*_urls`. Formats: JPEG/JPG, PNG (transparency not supported), BMP, WEBP; each side [240, 8000] px; aspect ratio ≤ 8:1; ≤ 20MB.
`last_frame_url`	string	URL of the last-frame image. Use together with first_frame_url. Same format limits as first_frame_url.
`reference_image_urls`	array	Reference images for the all-purpose reference mode, with up to 10 images. Correspond to Image1, Image2, … in the prompt according to array order. Specifications are the same as `first_frame_url`. Cannot be provided together with the first-frame/last-frame parameters.
`reference_video_urls`	array	Reference videos for the all-purpose reference mode, with up to 5 clips. Each clip must be 1–15 seconds, with a total duration ≤ 15 seconds. Correspond to Video1, Video2, … according to array order. Formats: mp4, mov; each side [240, 4096] px; aspect ratio ≤ 8:1; each file ≤ 100MB. There is an additional constraint on the output side: the input video duration + `duration` must not exceed 30 second
`reference_audio_urls`	array	Reference audio for the all-purpose reference mode, with up to 5 clips. Each clip must be 1–15 seconds, with a total duration ≤ 15 seconds. Correspond to Audio1, Audio2, … according to array order. Formats: wav, mp3; ≤ 15MB. Reference audio can be used as the only media input; pairing it with a reference image or video usually gives better results.
`reference_file_urls`	array	File-to-video generation. Up to 1 file. Cannot be provided together with `reference_link_urls`, or with the first-frame/last-frame parameters. Formats: docx/doc/xlsx/xls/pptx/ppt/pdf/txt/key/pages/numbers/md; ≤ 100MB; pdf/docx/ppt/key/pages, etc. ≤ 50 pages.
`reference_link_urls`	array	Link-to-video generation. Up to 1 publicly accessible webpage that does not require login. Cannot be provided together with `reference_file_urls`, or with the first-frame/last-frame parameters.
`resolution`	string	Output resolution. Default: 1080P. Allowed: `480P`, `720P`, `1080P`. Default: `1080P`.
`aspect_ratio`	string	Output aspect ratio. `adaptive` (default) automatically selects the ratio based on the input media and intent. Allowed: `adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`. Default: `adaptive`.
`duration`	integer	Output video duration in seconds. Default: 5. Without video input, the range is [2, 30]. With reference videos: input video duration + output duration ≤ 30. Pass `-1` to use an intelligent duration determined by the model. Default: `5`.
`audio`	boolean	Whether the output video includes an audio track. Default: true. Default: `true`.
`seed`	integer	Random seed used to reproduce results. If omitted, a random seed will be used.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/3-0-video-prime · Wan 3.0 - Video Prime · POST /v1/videos/generations

Field	Type	Details
`prompt`	string	Text prompt. Chinese and English are supported. Up to 20,000 characters. Required for text-to-video; for other modes, it is recommended to provide it together with media. In reference mode, use Image1/Video1/Audio1 to reference the provided materials.
`first_frame_url`	string	URL of the first-frame image. Up to 1 image, used strictly as the first frame of the video. Used for first-frame-to-video or first-and-last-frame-to-video generation. Cannot be provided together with `reference_*_urls`. Formats: JPEG/JPG, PNG (transparency not supported), BMP, WEBP; each side [240, 8000] px; aspect ratio ≤ 8:1; ≤ 20MB.
`last_frame_url`	string	URL of the last-frame image. Use together with first_frame_url. Same format limits as first_frame_url.
`reference_image_urls`	array	Reference images for all-purpose reference mode. Up to 10 images. Correspond to Image1, Image2, and so on in the prompt according to array order. Same specifications as `first_frame_url`. Cannot be provided together with the first-frame or last-frame image.
`reference_video_urls`	array	Reference videos for all-purpose reference mode. Up to 5 videos. Each video must be 1–15s, with a combined duration of ≤ 15s. Correspond to Video1, Video2, and so on according to array order. Formats: mp4, mov; each side [240, 4096] px; aspect ratio ≤ 8:1; each file ≤ 100MB. There is an additional output-side limit: the input video duration plus `duration` cannot exceed 30 seconds.
`reference_audio_urls`	array	Reference audio files for all-purpose reference mode. Up to 5 audio files. Each file must be 1–15s, with a combined duration of ≤ 15s. Correspond to Audio1, Audio2, and so on according to array order. Formats: wav, mp3; ≤ 15MB. Reference audio can be used as the only media input; pairing it with a reference image or video usually gives better results.
`reference_file_urls`	array	File-to-video generation. Up to 1 file. Cannot be provided together with `reference_link_urls`, or with the first-frame/last-frame image. Formats: docx/doc/xlsx/xls/pptx/ppt/pdf/txt/key/pages/numbers/md; ≤ 100MB; pdf/docx/ppt/key/pages, etc. ≤ 50 pages.
`reference_link_urls`	array	Link-to-video generation. Up to 1 publicly accessible webpage that does not require login. Cannot be provided together with `reference_file_urls`, or with the first-frame/last-frame image.
`resolution`	string	Output resolution level. Default: 1080P. Allowed: `480P`, `720P`, `1080P`. Default: `1080P`.
`aspect_ratio`	string	Output aspect ratio. `adaptive` (default) automatically selects the aspect ratio based on the input materials and intent. Allowed: `adaptive`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`. Default: `adaptive`.
`duration`	integer	Output video duration in seconds. Default: 5. When there is no video input, the value must be within [2, 30]. When reference videos are provided: input video duration plus output duration ≤ 30. Pass `-1` to use an intelligent duration determined by the model. Default: `5`.
`audio`	boolean	Whether the output video includes an audio track. Default: true. Default: `true`.
`seed`	integer	Random seed used to reproduce results. If omitted, a random seed is used.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Lip-sync and avatars

infinitalk/from-audio · Infinitalk - From Audio · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	URL of the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`audio_url` (required)	string	The URL of the audio file. (File URL after upload, not file content; Accepted types: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; Max size: 10.0MB)
`prompt` (required)	string	The text prompt to guide video generation. (Max length: 5000 characters)
`resolution`	string	Resolution of the video to generate. Must be either 480p or 720p. Allowed: `480p`, `720p`. Default: `480p`.
`seed`	number	Random seed for reproducibility. Valid range is 10000 to 1000000.

kling/ai-avatar-pro · Kling AI Avatar Pro · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	The URL of the image to use as your avatar (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`audio_url` (required)	string	The URL of the audio file (must be the URL of the uploaded file, not the file content; supported formats: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; audio size is limited to 100M, and the duration cannot exceed 5 minutes)
`prompt` (required)	string	Required, non-empty. Describe the avatar's expression, movement and camera; the speech comes from audio_url. Up to 5,000 characters.

kling/ai-avatar-standard · Kling AI Avatar Standard · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	The URL of the image to use as your avatar (File URL after upload, not file content; Accepted types: image/jpeg, image/png; Max size: 10.0MB)
`audio_url` (required)	string	The URL of the audio file (must be the URL of the uploaded file, not the file content; supported formats: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; audio size is limited to 100M, and the duration cannot exceed 5 minutes)
`prompt` (required)	string	Required, non-empty. Describe the avatar's expression, movement and camera; the speech comes from audio_url. Up to 5,000 characters.

omnihuman-1-5 · Omnihuman 1.5 · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	Portrait image URL. Supports any aspect ratio with subjects including people, pets, anime, etc. Accepted file types: image/jpeg, image/png, image/webp. Max file size: 10MB.
`mask_url`	array	Optional mask image URL(s). To have a specific subject in the image speak, use 'Subject Detection' to get the corresponding mask image and pass it as input. Accepted file types: image/jpeg, image/png, image/webp. Max file size: 10MB. Multiple file upload is supported, up to 5 files.
`audio_url` (required)	string	Audio URL. Duration must be less than 60 seconds (recommended 15 seconds or less; exceeding this will cause quality degradation). Accepted file types: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/ogg, audio/mp4. Max file size: 10MB.
`prompt`	string	Optional. Supported languages: Chinese, English, Japanese, Korean, Spanish, Indonesian. Up to 300 characters.
`output_resolution`	string	Output video resolution. - `720`: 720P - `1080`: 1080P (default) The output keeps the aspect ratio of the input image; 720 and 1080 are resolution tiers, not exact heights. The output is an MP4 as long as the audio. Allowed: `720`, `1080`. Default: `1080`.
`pe_fast_mode`	boolean	Fast mode. Sacrifices some quality to speed up generation. Default value: `false`. Default: `false`.
`seed`	integer	Random seed. Default is `-1` (random). When using the same positive integer and keeping all other parameters identical, the result will be highly consistent. Default: `-1`.

volcengine/video-to-video-lip-sync · Volcengine video to video lip sync · POST /v1/generations

Field	Type	Details
`mode` (required)	string	Service mode for lip-sync generation. - `lite`: For single-person frontal videos. Faster processing. - `basic`: For single-person complex scenes. Supports scene segmentation and speaker identification. Allowed: `lite`, `basic`.
`video_url` (required)	string	Video URL. Supported resolution: 360p–1080p. Videos above 1080p will be compressed to 1080p, while videos below 360p are not supported. Supported formats: MOV, MP4, HDR, MKV. Recommended codec: H.264. Other formats/codecs may be transcoded. Max file size: 500 MB. Bitrate: 1–30 Mbps. Frame rate: 24–60 fps.
`audio_url` (required)	string	Target pure vocal audio URL; used to drive video lip movements. Audio duration: over 1 s and up to 240 s in lite mode; over 1 s and up to 210 s in basic mode. Accepted file types: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg. Max file size: 10MB.
`separate_vocal`	boolean	Enable vocal separation to suppress background noise. Default value: `false`. Default: `false`.
`open_scenedet`	boolean	Whether to enable scene segmentation and speaker identification. Supported only in Basic mode. Default value: `false`. Default: `false`.
`align_audio`	boolean	Supported in Lite mode. Whether to loop the video when the audio is longer than the video. Default value: `true`. Default: `true`.
`align_audio_reverse`	boolean	Supported in Lite mode. Whether to loop the video in reverse (backward). Requires `align_audio` to be set to `true`. Default value: `false`. Default: `false`.
`templ_start_seconds`	number	Supported in Lite mode. Start time of the template video, in seconds. Default value: `0`. Default: `0`.

wan/2-2-a14b-speech-to-video-turbo · Wan - 2.2 A14B Speech to Video Turbo · POST /v1/generations

Field	Type	Details
`prompt` (required)	string	The text prompt used for video generation (Max length: 5000 characters)
`image_url` (required)	string	URL of the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`audio_url` (required)	string	The URL of the audio file (File URL after upload, not file content; Accepted types: audio/mp3, audio/wav, audio/ogg, audio/m4a, audio/flac, audio/aac, audio/x-ms-wma, audio/mpeg; Max size: 10.0MB)
`num_frames`	number	Number of frames to generate. Must be between 40 to 120, (must be multiple of 4) (Min: 40, Max: 120, Step: 4) (step: 4) Default: `80`.
`frames_per_second`	number	Frames per second of the generated video. Must be between 4 to 60. (Min: 4, Max: 60, Step: 1) (step: 1) Default: `16`.
`resolution`	string	Resolution of the generated video (480p, 580p, or 720p) Allowed: `480p`, `580p`, `720p`. Default: `480p`.
`negative_prompt`	string	Negative prompt for video generation (Max length: 500 characters)
`seed`	integer	Optional. Omit for a random seed.
`num_inference_steps`	number	Number of inference steps for sampling. Higher values give better quality but take longer (Min: 2, Max: 40, Step: 1) (step: 1) Default: `27`.
`guidance_scale`	number	Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality (Min: 1, Max: 10, Step: 0.1) (step: 0.1) Default: `3.5`.
`shift`	number	Shift value for the video. Must be between 1.0 and 10.0 (Min: 1, Max: 10, Step: 0.1) (step: 0.1) Default: `5`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-2-animate-move · Wan - Animate Move · POST /v1/generations

Field	Type	Details
`video_url` (required)	string	URL of the input video. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 10.0MB)
`image_url` (required)	string	URL of the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`resolution`	string	Resolution of the generated video (480p, 580p, or 720p). Allowed: `480p`, `580p`, `720p`. Default: `480p`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

wan/2-2-animate-replace · Wan - Animate Replace · POST /v1/generations

Field	Type	Details
`video_url` (required)	string	URL of the input video. (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 10.0MB)
`image_url` (required)	string	URL of the input image. (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`resolution`	string	Resolution of the generated video (480p, 580p, or 720p). Allowed: `480p`, `580p`, `720p`. Default: `480p`.
`nsfw_checker`	boolean	Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model.

Upscaling

grok-imagine/upscale · Grok Imagine - Video Upscale · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID from a previously successful video generation task. Required field. - task_id must be a successful grok-imagine/text-to-video or grok-imagine/image-to-video task. - The original video generation must have completed successfully - Only Omni AI–generated task IDs are supported
`resolution`	string	Video generation resolution. Allowed: `720p`, `1080p`. Default: `720p`.

recraft/crisp-upscale · Recraft - Crisp Upscale · POST /v1/generations

Field	Type	Details
`image` (required)	string	Image to upscale (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)

topaz/image-upscale · Topaz - Image Upscale · POST /v1/generations

Field	Type	Details
`image_url` (required)	string	Url of the image to be upscaled (File URL after upload, not file content; Accepted types: image/jpeg, image/png, image/webp; Max size: 10.0MB)
`upscale_factor` (required)	string	Factor to upscale the image by (e.g. 2 doubles width and height). Allowed: `1`, `2`, `4`. Default: `2`.

topaz/video-upscale · Topaz - Video Upscale · POST /v1/generations

Field	Type	Details
`video_url` (required)	string	URL of the video to upscale (File URL after upload, not file content; Accepted types: video/mp4, video/quicktime, video/x-matroska; Max size: 50.0MB)
`upscale_factor`	string	Upscale factor (string): "1", "2" (default) or "4". Allowed: `1`, `2`, `4`. Default: `2`.

Speech

elevenlabs/text-to-dialogue-v3 · elevenlabs/text-to-dialogue-v3 · POST /v1/generations

Field	Type	Details
`dialogue` (required)	array	Array of dialogue items. Each item contains text and voice. The total character count of all text fields combined must not exceed 5000 characters.
`stability`	number	Voice stability parameter. Must be one of the following values: 0.0, 0.5, or 1.0 Allowed: `0`, `0.5`, `1`. Default: `0.5`.
`language_code`	string	Language code for the speech. Default is empty string or omit the parameter for automatic language detection.

elevenlabs/text-to-speech-multilingual-v2 · elevenlabs/text-to-speech-multilingual-v2 · POST /v1/generations

Field	Type	Details
`text` (required)	string	The text to convert to speech (Max length: 5000 characters)
`voice` (required)	string	Voice ID from the list below. You can preview a voice by opening .mp3 in your browser (replace with the actual voice ID). For example: Available voices: EkK5I93UQWFDigLMpZcX - James - Husky, Engaging and Bold Z3R5wn05IrDiVCyEkUrK - Arabella - Mysterious and Emotive NNl6r8mD7vthiJatiJt1 - Bradford - Expressive and Articulate YOq2y2Up4RgXP2HyXjE5 - Xavier - Dominating, Metallic Announcer B8gJV1Ihpue Default: `EkK5I93UQWFDigLMpZcX`.
`stability`	number	Voice stability (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0.5`.
`similarity_boost`	number	Similarity boost (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0.75`.
`style`	number	Style exaggeration (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0`.
`speed`	number	Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. (Min: 0.7, Max: 1.2, Step: 0.01) (step: 0.01) Default: `1`.
`timestamps`	boolean	Whether to return timestamps for each word in the generated speech (Boolean value (true/false))
`previous_text`	string	The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. (Max length: 5000 characters)
`next_text`	string	The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. (Max length: 5000 characters)
`language_code`	string	Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. (Max length: 500 characters)

elevenlabs/text-to-speech-turbo-2-5 · elevenlabs/text-to-speech-turbo-2-5 · POST /v1/generations

Field	Type	Details
`text` (required)	string	The text to convert to speech (Max length: 5000 characters)
`voice`	string	Voice ID from the list below. You can preview a voice by opening .mp3 in your browser (replace with the actual voice ID). For example: Available voices: EkK5I93UQWFDigLMpZcX - James - Husky, Engaging and Bold Z3R5wn05IrDiVCyEkUrK - Arabella - Mysterious and Emotive NNl6r8mD7vthiJatiJt1 - Bradford - Expressive and Articulate YOq2y2Up4RgXP2HyXjE5 - Xavier - Dominating, Metallic Announcer B8gJV1Ihpue Default: `EkK5I93UQWFDigLMpZcX`.
`stability`	number	Voice stability (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0.5`.
`similarity_boost`	number	Similarity boost (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0.75`.
`style`	number	Style exaggeration (0-1) (Min: 0, Max: 1, Step: 0.01) (step: 0.01) Default: `0`.
`speed`	number	Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. (Min: 0.7, Max: 1.2, Step: 0.01) (step: 0.01) Default: `1`.
`timestamps`	boolean	Whether to return timestamps for each word in the generated speech (Boolean value (true/false))
`previous_text`	string	The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. (Max length: 5000 characters)
`next_text`	string	The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. (Max length: 5000 characters)
`language_code`	string	Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. (Max length: 500 characters)

google/gemini-2-5-pro-tts · Gemini 2.5 Pro Text to Speech · POST /v1/generations

Field	Type	Details
`temperature`	number	Sampling temperature, e.g., 1 Default: `1`.
`scene`	string	Scene description, e.g., "A quiet, warm room with a fireplace crackling softly." Default: .
`sample_context`	string	Sample context/overall tone, e.g., "Audiobook style narration. Tone is gentle and inviting." Default: .
`speakers` (required)	array	List of speaker configurations
`dialogue_turns` (required)	array	List of dialogue turns, output in sequential order

google/gemini-3-1-flash-tts · Gemini 3.1 Flash Text to speech · POST /v1/generations

Field	Type	Details
`temperature`	number	Sampling temperature, e.g., 1 Default: `1`.
`scene`	string	Scene description, e.g., "A quiet, warm room with a fireplace crackling softly." Default: .
`sample_context`	string	Sample context/overall tone, e.g., "Audiobook style narration. Tone is gentle and inviting." Default: .
`speakers` (required)	array	List of speaker configurations
`dialogue_turns` (required)	array	List of dialogue turns, output in sequential order

google/gemini-3-8-flash-lite-tts · Gemini 3.8 Flash Lite Text to speech · POST /v1/generations

Field	Type	Details
`temperature`	number	Sampling temperature, e.g., 1 Default: `1`.
`speakers` (required)	array	List of speaker configurations. Each speaker uses either `voice_name` (preset voice) or `replica` (voice clone); the two are mutually exclusive. If neither is sent, the speaker defaults to `Fola`.
`filler_words`	boolean	Whether to insert filler words in two-speaker dialogue. Off by default (omit this field); when enabled, the request includes `"filler_words": true`. Only takes effect when `speakers` has two speakers (e.g. Speaker 1 and Speaker 2). When two people are speaking, you can turn on this switch. Default: `false`.
`dialogue_turns` (required)	array	List of dialogue turns, output in sequential order

google/gemini-3-8-flash-tts · Gemini 3.8 Flash Text to speech · POST /v1/generations

Field	Type	Details
`temperature`	number	Sampling temperature, e.g., 1 Default: `1`.
`speakers` (required)	array	List of speaker configurations. Each speaker uses either `voice_name` (preset voice) or `replica` (voice clone); the two are mutually exclusive. If neither is sent, the speaker defaults to `Fola`.
`filler_words`	boolean	Whether to insert filler words in two-speaker dialogue. Off by default (omit this field); when enabled, the request includes `"filler_words": true`. Only takes effect when `speakers` has two speakers (e.g. Speaker 1 and Speaker 2). When two people are speaking, you can turn on this switch. Default: `false`.
`dialogue_turns` (required)	array	List of dialogue turns, output in sequential order

Audio tools

elevenlabs/audio-isolation · elevenlabs/audio-isolation · POST /v1/generations

Field	Type	Details
`audio_url` (required)	string	URL of the audio file to isolate voice from (File URL after upload, not file content; Accepted types: audio/mpeg, audio/wav, audio/x-wav, audio/aac, audio/mp4, audio/ogg; Max size: 10.0MB)

Music suite

suno/add-instrumental · Add Instrumental to Music · POST /v1/generations

Field	Type	Details
`upload_url` (required)	string	URL of the uploaded audio file. Required. Source audio (`upload_url`) is enough to generate once `title`, `negative_tags`, and `tags` are provided.
`model`	string	The AI model version to use for generation. - Available options: - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. - `V5_5` (Discontinued): Custom Models Tailored to Your Unique Allowed: `V4_5PLUS`, `V5`, `V5_5`, `V6`, `V6_MINI`, `V6_WILD`. Default: `V6`.
`title` (required)	string	Title of the generated music. Required. Will be displayed in the player interface and file name.
`negative_tags` (required)	string	Music styles or characteristics to exclude from the generated audio. Required. Used to avoid specific unwanted music elements.
`tags` (required)	string	Music styles or tags to include in the generated music. Required. Defines the desired music style and characteristics.
`vocal_gender`	string	Vocal gender preference. Optional. 'm' for male, 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Allowed: `m`, `f`.
`style_weight`	number	Adherence strength to specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation level. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Relative weight of audio elements. Optional. Range 0–1, up to 2 decimal places.
`lyrics`	string	Lyrics for the generated audio. Optional. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate once `title`, `negative_tags`, and `tags` are provided.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.

suno/add-vocals · Add Vocals to Music · POST /v1/generations

Field	Type	Details
`prompt`	string	Prompt for generating audio. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters.
`model`	string	The AI model version to use for generation. - Available options: - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. - `V5_5` (Discontinued): Custom Models Tailored to Your Unique Allowed: `V4_5PLUS`, `V5`, `V5_5`, `V6`, `V6_MINI`, `V6_WILD`. Default: `V6`.
`title` (required)	string	Music title. Required. Will be displayed in the player interface and file name.
`negative_tags` (required)	string	Excluded music styles. Required. Used to avoid including specific styles or elements in the generated music.
`style` (required)	string	Music style. Required. Such as jazz, electronic, classical and other music types.
`vocal_gender`	string	Vocal gender preference. Optional. 'm' for male, 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Allowed: `m`, `f`.
`style_weight`	number	Adherence strength to specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation level. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Relative weight of audio elements. Optional. Range 0–1, up to 2 decimal places.
`upload_url` (required)	string	URL of the uploaded audio file. Required. Source audio (`upload_url`) is enough to generate once `title`, `negative_tags`, and `style` are provided.
`lyrics`	string	Lyrics for the generated audio. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate once `title`, `negative_tags`, and `style` are provided.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.

suno/boost-music-style · Boost Music Style · POST /v1/generations

Field	Type	Details
`content` (required)	string	Style description. Please describe in concise and clear language the music style you expect to generate. Example: 'Pop, Mysterious'

suno/check-voice · Suno Voice Check Availability API · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID that needs to be checked

suno/convert-to-wav-format · Convert to WAV Format · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Unique identifier of the music generation task. This should be a task_id returned from either the "Generate Music" or "Extend Music" endpoints.
`audio_id` (required)	string	Unique identifier of the specific audio track to convert. This ID is returned in the webhook_url data after music generation completes.

suno/cover-generate · Generate Music Cover · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Original music task ID, should be the task_id returned by the music generation interface.

suno/create-music-video · Create Music Video · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Unique identifier of the music generation task. This should be a task_id returned from either the "Generate Music" or "Extend Music" endpoints.
`audio_id` (required)	string	Unique identifier of the specific audio track to visualize. This ID is returned in the webhook_url data after music generation completes.
`author`	string	Artist or creator name to display as a signature on the video cover. Maximum 50 characters. This creates attribution for the music creator.
`domain_name`	string	Website or brand to display as a watermark at the bottom of the video. Maximum 50 characters. Useful for promotional branding or attribution.

suno/create-voice · Suno Voice Create Custom Voice API · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID
`verify_url` (required)	string	Audio URL for the user's recording of the server-returned `validateInfo` validation phrase. For best voice generation results, recording the phrase in a singing voice rather than plain speech is recommended. [Required]
`voice_name`	string	Voice name
`description`	string	Voice description
`style`	string	Voice style
`singer_skill_level`	string	Singer skill level. Supported: beginner, intermediate, advanced, professional Allowed: `beginner`, `intermediate`, `advanced`, `professional`. Default: `beginner`.

suno/extend · Extend Music · POST /v1/generations

Field	Type	Details
`audio_id` (required)	string	Unique identifier of the audio track to extend. Required for all extension requests.
`prompt`	string	Lyrics for the extended audio. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`audio_id`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`style`	string	Music style specification for the extended audio. Optional. - Not required. Source audio (`audio_id`) is enough to generate. - Character limits by model: - V4 (Discontinued): Maximum 200 characters - V4_5 & V4_5PLUS (Discontinued): Maximum 1000 characters - V4_5ALL (Discontinued): Maximum 1000 characters - V5_5 & V5 (Discontinued): Maximum 1000 characters - **V6, V6_MINI, and V6_WI
`title`	string	Title for the extended music track. Optional. - Maximum 100 characters. - Displayed in player interfaces and filenames.
`continue_at`	number	The time point (in seconds) from which to start extending the music. - Value range: greater than 0 and less than the total duration of the generated audio. - Specifies the position in the original track where the extension should begin.
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`, `V5_5`, `V6`, `V6_WILD`, `V6_MINI`.
`negative_tags`	string	Music styles or traits to exclude from the extended audio. Optional. Use to avoid specific undesired characteristics.
`vocal_gender`	string	Vocal gender preference. Optional. 'm' denotes a male voice, and 'f' denotes a female voice. In practice, this parameter only influences the probability and does not guarantee strict adherence to the gender instruction. This parameter is not required if `instrumental` is set to `true`. Allowed: `m`, `f`.
`style_weight`	number	Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Balance weight for audio features vs. other factors. Optional. Range 0–1, up to 2 decimal places.
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	The persona model is only applicable to the V5 (deactivated), V5.5 (deactivated), V6, V6_MINI, and V6_WILD models. Allowed: `style_persona`, `voice_persona`.
`instrumental`	boolean	Indicates whether it is an instrumental track. If true, passing the `lyrics`, `prompt`, and `vocal_gender` parameters is prohibited. Default: `false`.
`lyrics`	string	Lyrics for the extended audio. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`audio_id`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.

suno/generate · Generate Music · POST /v1/generations

Field	Type	Details
`prompt`	string	A description of the desired audio content. Optional. - Custom mode (`custom_mode=true`): When provided, the prompt is used strictly as lyrics and sung in the generated track. Character limits by model: - V4: Maximum 3000 characters - V4_5, V4_5PLUS, V4_5ALL, V5_5, V5: Maximum 5000 characters - Non-custom mode (`custom_mode=false`): When provided, the prompt serves as the core idea. Lyrics are gen
`style`	string	Music style specification for the generated audio. - Character limits by model: - V4 (Discontinued): Maximum 200 characters - V4_5 and V4_5PLUS (Discontinued): Maximum 1000 characters - V4_5ALL (Discontinued): Maximum 1000 characters - V5_5 and V5 (Discontinued): Maximum 1000 characters - V6, V6_MINI, and V6_WILD: Maximum 1000 characters - Common examples: Jazz, Classical, Elec
`title`	string	Title for the generated music track. - Required in Custom Mode (`custom_mode: true`). - Max length: 80 characters. - Will be displayed in player interfaces and filenames.
`custom_mode` (required)	boolean	Determines whether advanced parameter customization is enabled. - If `true`: Allows detailed control - If `false`: Simplified mode
`instrumental` (required)	boolean	Whether to generate instrumental music (no vocals). See Parameter Details for the fields required in each mode.
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`, `V5_5`, `V6`, `V6_MINI`, `V6_WILD`.
`negative_tags`	string	Music styles or traits to exclude from the generated audio. Optional. Use to avoid specific styles.
`vocal_gender`	string	Vocal gender preference. Optional. Use `m` for male and `f` for female. This parameter is only effective when `custom_mode` is true. In practice, it only increases probability and cannot guarantee male/female voice instructions are followed. Allowed: `m`, `f`.
`style_weight`	number	Only available when Custom Mode (`custom_mode: true`) is enabled. Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Only available when Custom Mode (`custom_mode: true`) is enabled. Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Only available when Custom Mode (`custom_mode: true`) is enabled. Relative weight of audio features. Optional. Range 0–1, up to 2 decimal places. - `audio_weight` is not supported when there are no vocals
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	Persona model. Only available for V5 (Discontinued), V5.5 (Discontinued), V6, V6_MINI, and V6_WILD. Allowed: `style_persona`, `voice_persona`.
`duration`	number	Target length in seconds (10–360). Optional; if omitted, the model chooses the length. Only valid when `custom_mode` is true and the model is V5_5 (Discontinued), V6, V6_MINI, or V6_WILD.
`image_urls`	array	Image references. Only effective when `custom_mode=false`. - Optional - Up to 5 images; each image must not exceed 10 MB - Supported formats: `jpeg`, `png`, `webp`, and `bmp`
`variety`	number	Only available when Custom Mode (`custom_mode: true`) is enabled. Controls the diversity and stylistic variation of generated results. Optional. Range 0–4, integer, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different s Default: `1`.
`lyrics`	string	Lyrics for the generated audio. Optional. - V6: Maximum 5000 characters. - When `custom_mode=true`, `lyrics` is used as lyrics first; if `lyrics` is not provided, `prompt` is used as lyrics. - When `custom_mode=false`, `lyrics` is used as a lyrics attachment and can be used together with the audio description in `prompt`.
`audio_urls`	array	Audio references. Only effective when `custom_mode=false`. - Optional - Audio duration must be between 6 seconds and 30 minutes; each audio file must not exceed 500 MB
`video_urls`	array	Video references. Only effective when `custom_mode=false`. - Optional - Up to 1 video file; each file must not exceed 100 MB, duration must not exceed 241 seconds, with no minimum duration - Supported formats: mp4, mov, and webm

suno/generate-lyrics · Generate Lyrics · POST /v1/generations

Field	Type	Details
`prompt` (required)	string	Description of the desired lyrics content. Be specific about theme, mood, style, or story elements you want in the lyrics. More detailed prompts yield better results. The maximum word limit is 200 characters.

suno/generate-midi-from-audio · Generate MIDI from Audio · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID from a completed vocal separation. This should be the task_id returned from the Vocal & Instrument Stem Separation endpoint.
`audio_id`	string	The id of a stem from the separation callback (vocal_removal_info.origin_data[].id). If omitted, MIDI is generated from all stems.

suno/generate-persona · Generate Persona · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Unique identifier of the original music generation task. Generated by model suno/generate or suno/extend.
`audio_id` (required)	string	Unique identifier of the audio track to create Persona for. This ID is returned in the webhook_url data after music generation completes.
`name` (required)	string	Name for the Persona. A descriptive name that captures the essence of the musical style or character.
`description` (required)	string	Detailed description of the Persona's musical characteristics, style, and personality. Be specific about genre, mood, instrumentation, and vocal qualities.
`vocal_start`	number	Start time (in seconds) for Persona analysis segment extraction. Used to specify the time point in the audio from which to extract the segment for Persona analysis. Must be less than vocal_end, and vocal_end - vocal_start must be between 10–30 seconds. Defaults to 0.0. Default: `0`.
`vocal_end`	number	End time (in seconds) for Persona analysis segment extraction. Together with vocal_start, used to specify the time range for analysis. vocal_end - vocal_start must be between 10–30 seconds. Defaults to 30.0. Default: `30`.
`style`	string	Optional. Used to supplement the description of the music style tag corresponding to the Persona, such as "Electronic Pop", "Jazz Trio", etc.

suno/mashup · Generate Mashup Music · POST /v1/generations

Field	Type	Details
`upload_url_list` (required)	array	Array of audio file URLs to mashup. Provide 2 audio URLs. Only the first 2 are used. Each URL must be publicly accessible.
`prompt`	string	A description of the desired audio content. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters.
`style` (required)	string	Music style specification for the generated audio. Required. - Character limits by model: - V4 (Discontinued): Maximum 200 characters - V4_5 & V4_5PLUS (Discontinued): Maximum 1000 characters - V4_5ALL (Discontinued): Maximum 1000 characters - V5 & V5_5 (Discontinued): Maximum 1000 characters - V6, V6_MINI & V6_WILD: Maximum 1000 characters - Common examples: Jazz, Classical, E
`title` (required)	string	Title for the generated music track. Required. - Character limits by model: - V4 (Discontinued): Maximum 80 characters - V4_5 & V4_5PLUS (Discontinued): Maximum 100 characters - V4_5ALL (Discontinued): Maximum 80 characters - V5 & V5_5 (Discontinued): Maximum 100 characters - V6, V6_MINI & V6_WILD: Maximum 100 characters - Will be displayed in player interfaces and filenames.
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`, `V5_5`, `V6`, `V6_WILD`, `V6_MINI`.
`vocal_gender`	string	Vocal gender preference for the singing voice. Optional. Use 'm' for male and 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Allowed: `m`, `f`.
`style_weight`	number	Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Balance weight for audio features vs. other factors. Optional. Range 0–1, up to 2 decimal places.
`duration`	integer	Audio duration in seconds. Optional. Range 10–360, default 20. Valid when `model` is ~~V5_5~~ (Discontinued), V6, V6_MINI, or V6_WILD. Default: `20`.
`lyrics`	string	Lyrics for the mashup. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	Persona model. Optional. Use `style_persona` for Generate Persona IDs, or `voice_persona` for Suno Voice IDs. Default: `style_persona`. Available for V5 (Discontinued), V5_5 (Discontinued), V6, V6_MINI, and V6_WILD. Allowed: `style_persona`, `voice_persona`. Default: `style_persona`.

suno/regenerate-phrase · Suno Voice Regenerate Verification Phrase · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Task ID

suno/replace-section · Replace Music Section · POST /v1/generations

Field	Type	Details
`prompt` (required)	string	The lyrics after replacement. Required.
`tags` (required)	string	Style tags for the music, such as jazz or electronic. Required.
`title` (required)	string	The title of the music. Required.
`negative_tags`	string	Music styles to exclude, used to prevent specific stylistic elements from appearing in the replacement section.
`infill_start_s` (required)	number	The point in time, in seconds, at which replacement starts, rounded to 2 decimal places. Required. Must be less than infill_end_s, and the difference between infill_end_s and infill_start_s must be at least 10 seconds.
`infill_end_s` (required)	number	The point in time, in seconds, at which replacement ends, rounded to 2 decimal places. Required. Must be greater than infill_start_s, and the difference between infill_end_s and infill_start_s must be at least 10 seconds.
`full_lyrics` (required)	string	The complete modified lyrics, combining the modified and unmodified lyrics. Required. This parameter contains the complete lyrics text that will be used for the entire song after section replacement.
`lyrics`	string	Lyrics for the replaced segment. Optional. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters.
`vocal_gender`	string	Vocal gender preference. Optional. 'm' for male, 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Allowed: `m`, `f`.
`style_weight`	number	Adherence strength to specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation level. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Relative weight of audio elements. Optional. Range 0–1, up to 2 decimal places.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	Persona model. Optional. Use `style_persona` for Generate Persona IDs, or `voice_persona` for Suno Voice IDs. Default: `style_persona`. Available for V5 (Discontinued), V5_5 (Discontinued), V6, V6_MINI, and V6_WILD. Allowed: `style_persona`, `voice_persona`. Default: `style_persona`.

suno/separate-vocals · Vocal & Instrument Stem Separation · POST /v1/generations

Field	Type	Details
`type`	string	Separation type, options: - separate_vocal: Separate vocals and accompaniment, generating a vocal track and an instrumental track. - split_stem: Separate various instrument sounds, generating multiple instrument tracks. - split_stem_advanced: Advanced multi-track separation, supporting the specification of a particular instrument track to generate finer instrument tracks. Allowed: `separate_vocal`, `split_stem`, `split_stem_advanced`. Default: `separate_vocal`.
`stem_name`	string	Only used when `type` is `split_stem_advanced` to request a specific stem track/instrument name.

suno/sounds · Generate sounds · POST /v1/generations

Field	Type	Details
`prompt` (required)	string	Description of the sound (max 500 characters).
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V5`, `V5_5`, `V6`, `V6_WILD`, `V6_MINI`.
`sound_loop`	boolean	Whether the generated sound loops seamlessly. Default: `false`.
`sound_tempo`	integer	Tempo in BPM (1–300). Omit for automatic tempo.
`sound_key`	string	Musical key. Default "Any" (automatic). Allowed: `Any`, `Cm`, `C#m`, `Dm`, `D#m`, `Em`, `Fm`, `F#m`, `Gm`, `G#m`, `Am`, `A#m`, `Bm`, `C`, `C#`, `D`, `D#`, `E`, `F`, `F#`, `G`, `G#`, `A`, `A#`, `B`. Default: `Any`.
`grab_lyrics`	boolean	Whether to capture the lyrics subtitles Will the interface be called after completion to obtain the lyrics subtitles? Default: `false`.

suno/suno-recovery-audio · Recovery Audio · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	The original music generation task ID for which the audio link needs to be restored.

suno/timestamped-lyrics · Get Timestamped Lyrics · POST /v1/generations

Field	Type	Details
`task_id` (required)	string	Unique identifier of the music generation task. This should be a task_id returned from either the "Generate Music" or "Extend Music" endpoints.
`audio_id` (required)	string	Unique identifier of the specific audio track for which to retrieve lyrics. This ID is returned in the webhook_url data after music generation completes.

suno/upload-and-cover-audio · Upload And Cover Audio · POST /v1/generations

Field	Type	Details
`upload_url` (required)	string	The URL of the source audio file to cover. Required. Source audio (`upload_url`) is enough to generate. Ensure the uploaded audio does not exceed 8 minutes in length.
`prompt`	string	Lyrics for the covered audio. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`style`	string	The music style or genre for the audio. Optional. - Not required. Source audio (`upload_url`) is enough to generate. - Character limits by model: - V4 (Discontinued): Maximum 200 characters - V4_5 & V4_5PLUS (Discontinued): Maximum 1000 characters - V4_5ALL (Discontinued): Maximum 1000 characters - V5_5 & V5 (Discontinued): Maximum 1000 characters - V6, V6_MINI, and V6_WILD: Ma
`title`	string	The title of the generated music track. Optional. - Maximum 80 characters. - Displayed in player interfaces and filenames.
`instrumental` (required)	boolean	Determines if the audio should be instrumental (no lyrics). - If `true`: generate instrumental music (no vocals). Do not pass `lyrics`, `prompt`, or `vocal_gender`. - If `false`: use `lyrics` as lyrics (fall back to `prompt` if `lyrics` is not provided).
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`, `V5_5`, `V6`, `V6_WILD`, `V6_MINI`.
`negative_tags`	string	Music styles or traits to exclude from the generated audio. - Optional. Use to avoid specific styles. Example: "Heavy Metal, Upbeat Drums"
`vocal_gender`	string	Vocal gender preference for the singing voice. Optional. Use 'm' for male and 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Do not pass this parameter when `instrumental` is `true`. Allowed: `m`, `f`.
`style_weight`	number	Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Balance weight for audio features vs. other factors. Optional. Range 0–1, up to 2 decimal places.
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	Persona model: style_persona or voice_persona. Available for V6, V6_MINI and V6_WILD. Allowed: `voice_persona`, `style_persona`.
`duration`	integer	Target length in seconds (10–360). Optional; if omitted, the model chooses the length. Valid when `model` is ~~V5_5~~ (Discontinued), V6, V6_MINI, or V6_WILD.
`lyrics`	string	Lyrics for the covered audio. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.

suno/upload-and-extend-audio · Upload And Extend Audio · POST /v1/generations

Field	Type	Details
`upload_url` (required)	string	The URL of the source audio file to extend. Required. Source audio (`upload_url`) is enough to generate. Ensure the uploaded audio does not exceed 8 minutes in length.
`instrumental`	boolean	Determines whether the audio is instrumental (without lyrics). Optional; defaults to `false`. - If `true`: generate instrumental music (no vocals). Do not pass `lyrics`, `prompt`, or `vocal_gender`. - If `false`: use `lyrics` as lyrics (fall back to `prompt` if `lyrics` is not provided). Default: `false`.
`prompt`	string	Lyrics for the extended audio. Optional. - Used as lyrics only when `lyrics` is not provided. If `lyrics` is present, `prompt` is not used as lyrics. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`style`	string	Music style, e.g., Jazz, Classical, Electronic. Optional. - Not required. Source audio (`upload_url`) is enough to generate. - Character limits by model: - V6, V6_MINI & V6_WILD: Maximum 1000 characters - V5_5 & V5 (Discontinued): Maximum 1000 characters - V4_5PLUS & V4_5 (Discontinued): Maximum 1000 characters - V4_5ALL (Discontinued): Maximum 1000 characters - V4 (Discontinue
`title`	string	Music title. Optional. - Maximum 100 characters. - Displayed in player interfaces and filenames.
`continue_at`	number	The time point (in seconds) from which to start extending the music. - Value range: greater than 0 and less than the total duration of the uploaded audio. - Specifies the position in the original track where the extension should begin.
`model` (required)	string	Required. Use V6, V6_MINI or V6_WILD. - `V6_WILD`: Pushes creative boundaries for bolder, more distinctive musical expression. - `V6_MINI`: Lightweight and fast, balancing quality and speed for effortless creation. - `V6`: Greater musical expression with more natural vocals and richer details. Allowed: `V4`, `V4_5`, `V4_5PLUS`, `V4_5ALL`, `V5`, `V5_5`, `V6`, `V6_WILD`, `V6_MINI`.
`negative_tags`	string	Music styles to exclude from generation
`vocal_gender`	string	Vocal gender preference for the singing voice. Optional. Use 'm' for male and 'f' for female. Based on practice, this parameter can only increase the probability but cannot guarantee adherence to male/female voice instructions. Do not pass this parameter when `instrumental` is `true`. Allowed: `m`, `f`.
`style_weight`	number	Strength of adherence to the specified style. Optional. Range 0–1, up to 2 decimal places.
`weirdness_constraint`	number	Controls experimental/creative deviation. Optional. Range 0–1, up to 2 decimal places.
`audio_weight`	number	Balance weight for audio features vs. other factors. Optional. Range 0–1, up to 2 decimal places.
`persona_id`	string	Persona ID or Voice ID to apply to the generated music. Optional. Use this to apply a specific persona style to your music generation. To generate a Persona ID, use the Generate Persona endpoint to create a personalized music Persona based on generated music. To generate a Voice ID, use the Generate Voice endpoint.
`persona_model`	string	The persona model is only available for models version V5 (Discontinued), V5_5 (Discontinued), V6, V6_MINI, and V6_WILD. Allowed: `style_persona`, `voice_persona`.
`lyrics`	string	Lyrics for the extended audio. Optional. - Takes priority over `prompt` as lyrics. If omitted, `prompt` is used as lyrics when provided. - V6, V6_MINI, and V6_WILD: Maximum 5000 characters. - Not required. Source audio (`upload_url`) is enough to generate. - Do not pass this parameter when `instrumental` is `true`.
`variety`	integer	Controls the diversity and stylistic variation of generated results. Optional. Integer range 0–4, default 1. - `0`: off (exact style) — fully off, strictly the same style - `1`: normal (balanced variety) — default, balances stability and diversity - `2`: high (distinct styles) — produces results with clearly different styles - `3`: extra (bold exploration) — higher variation, encou Default: `1`.

suno/validation-phrase · Suno Voice Generate Verification Phrase API · POST /v1/generations

Field	Type	Details
`voice_url` (required)	string	The original recording URL uploaded by the user [Required]
`vocal_start_s` (required)	integer	Start time (in seconds) for extracting the vocal segment [Required]
`vocal_end_s` (required)	integer	End time (in seconds) for extracting the vocal segment, must be greater than vocal_start_s [Required]
`language`	string	Verify the language of the short phrase. Supported languages include: English (en), Chinese (zh), Spanish (es), French (fr), Portuguese (pt), German (de), Japanese (ja), Korean (ko), Hindi (hi), and Russian (ru).

Voice and audio endpoints

Model	Endpoint	What it does
`voice-library-tts`	`POST /v1/audio/speech`	Text to speech with thousands of voices plus your cloned voices
`voice-library-dialogue`	`POST /v1/audio/dialogue`	Multi-speaker dialogue
`elevenlabs-scribe`	`POST /v1/audio/transcriptions`	Speech to text with word timings
`eleven_text_to_sound_v2`	`POST /v1/audio/sound-effects`	Sound effects
`suno-music`	`POST /v1/audio/music`	Songs from a description or your lyrics
`eleven_multilingual_sts_v2`	`POST /v1/audio/voice-changer`	Speech to speech
`voice-isolation`	`POST /v1/audio/voice-isolation`	Background noise removal
`dubbing`	`POST /v1/audio/dubbing`	Dubbing into another language

Model reference

Contents

Language models

Image models with common fields

Video models with common fields

Image

Video

Lip-sync and avatars

Upscaling

Speech

Audio tools

Music suite

Voice and audio endpoints