Features
The Omni API puts language models, image and video generation, voice, music and transcription behind one API key and one prepaid balance. Each feature below has its endpoints, models, a working example, pricing and limits.
LLM API for GPT, Claude and Gemini with one key
Call GPT-6.1, Claude Opus 5.5, Claude Sonnet 5, Gemini 3.8 and more through one OpenAI-compatible API key, with streaming, at about 25% below the vendors' list prices.
Image generationImage generation API: GPT Image 2, Nano Banana and Seedream
Generate and edit images with GPT Image 2, Nano Banana, Seedream 5 and more through one API, with up to ten reference images, async tasks and webhooks.
Video generationAI video generation API: Kling, Veo, Seedance and Hailuo
Create text-to-video and image-to-video clips with Kling 3.0, Veo 3.1, Seedance 2 and Hailuo through one API key, with async tasks, webhooks and per-clip pricing.
Text to speechText-to-speech API with ElevenLabs and MiniMax voices
Turn text into natural speech with ElevenLabs, MiniMax, Edge, Kokoro and Fish Audio voices, multi-speaker dialogue and your own cloned voices.
Voice cloning and dubbingVoice cloning, voice changer and dubbing API
Clone a voice from a short sample, change the voice in a recording, isolate speech from noise, and dub audio into other languages through one API.
Speech to textSpeech-to-text API with word-level timings and SRT
Transcribe audio and video files up to 200 MB with word-level timings, SRT subtitles and audio-event tagging through one API key.
Music and sound effectsAI music and sound effects API
Generate full songs with lyrics or instrumentals, and sound effects up to 30 seconds, through one API with per-job pricing.
Every feature uses the same key and the same credit.
Get your API key →