REretellai

POST /clone-voice

Changed on

Clone a voice from audio files

Request

  • Base URL
    https://api.retellai.com
  • Auth
    HTTP bearer

Request body multipart/form-data

filesstring[] required

Audio files to use for voice cloning. Up to 25 files allowed. For Cartesia and MiniMax, only 1 file is supported. For Inworld, up to 3 files are supported.

voice_namestring required

Name for the cloned voice

voice_provider'elevenlabs' | 'cartesia' | 'minimax' | 'fish_audio' | 'platform' | 'inworld' required

Voice provider to use for cloning.

Response

Voice cloned successfully

voice_idstring required

Unique id for the voice.

voice_namestring required

Name of the voice.

provider'elevenlabs' | 'openai' | 'cartesia' | 'minimax' | 'fish_audio' | 'inworld' | 'platform' | 'xai' required

Indicates the provider of voice. xai voices can only be used with the grok-voice-3.0 speech-to-speech model.

accentstring

Accent annotation of the voice.

gender'male' | 'female' required

Gender of voice.

agestring

Age annotation of the voice.

avatar_urlstring

URL to the avatar image of the voice.

preview_audio_urlstring

URL to the preview audio of the voice.

Example response

{
  "voice_id": "retell-Cimo",
  "voice_name": "Adrian",
  "provider": "elevenlabs",
  "accent": "American",
  "gender": "male",
  "age": "Young",
  "avatar_url": "https://retell-utils-public.s3.us-west-2.amazonaws.com/customvoice-icon.png",
  "preview_audio_url": "https://retell-utils-public.s3.us-west-2.amazonaws.com/adrian.mp3"
}

Changes

  • f3087f7a3c84Revision changes
    • warning

      added the new xai enum value to the response property for the response status

    • info

      added the optional property to the response with the status

  • ca41f0dbb297Revision changes
    • warning

      added the new inworld enum value to the response property for the response status

    • info

      added the new inworld enum value to the request property