Voice cloning, voice changer and dubbing API

Upload a voice sample of up to 10 MB to create a private cloned voice you can use anywhere a voice is accepted. Related endpoints change the voice in an existing recording, remove background noise, and dub audio into another language.

Who it is for

Creators who want their own voice in generated audio
Localization teams dubbing content
Apps cleaning up user-recorded audio

How it works

Send a clean sample of the voice (multipart file or a public file_url).
Use the returned clone_ id with speech, dialogue, voice changer or dubbing.
Delete it any time with DELETE /v1/voices/clone/{voice_id}.

Endpoints

Method	Path	What it does
`POST`	`/v1/voices/clone`	Create a cloned voice
`POST`	`/v1/audio/voice-changer`	Speech to speech
`POST`	`/v1/audio/voice-isolation`	Remove background noise
`POST`	`/v1/audio/dubbing`	Dub into another language

Models

Pass one of these as model (or voice_id for voices). The full, current list with prices is at /v1/models.

clone_… voices
eleven_multilingual_sts_v2

Example

curl https://omni-api.rcinc.app/v1/voices/clone \
  -H "Authorization: Bearer $OMNI_KEY" \
  -F name="My narrator" -F audio_file=@sample.mp3

# -> {"voice_id":"clone_123", ...}  then use voice_id "clone_123" with /v1/audio/speech

Pricing

Voice changer, isolation and dubbing are charged per job from the provider's actual cost; each task shows its charge. See the pricing page for the full comparison.

Limits

Only clone voices you have the right to use.
Direct uploads are limited to about 4 MB; send larger files as file_url.
Voice isolation needs at least 5 seconds of audio.