API Reference

Voices

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Clone a voice

voices.clone(VoiceCloneParams**kwargs) -> VoiceCloneResponse

POST/voices/clone

Clone a voice from an audio recording. Send audio as a base64-encoded string. The cloned voice will be available in GET /voices.

ParametersExpand Collapse

audio: str

Base64-encoded audio data (max ~7.5MB decoded)

maxLength10000000

content_type: Literal["audio/webm", "audio/wav", "audio/mpeg", 3 more]

MIME type of the audio

One of the following:

"audio/webm"

"audio/wav"

"audio/mpeg"

"audio/ogg"

"audio/mp4"

"video/webm"

language: Literal["en", "fr", "es", 5 more]

Language of the voice

One of the following:

"en"

"fr"

"es"

"de"

"it"

"pt"

"ru"

"zh"

name: str

Name for the cloned voice

minLength1

ReturnsExpand Collapse

class VoiceCloneResponse: …

id: str

cartesia_voice_id: str

created_at: str

language: str

name: str

Clone a voice

Python

HTTP

TypeScript

Python

Ruby

import os
from revox import Revox

client = Revox(
    api_key=os.environ.get("REVOX_API_KEY"),  # This is the default and can be omitted
)
response = client.voices.clone(
    audio="audio",
    content_type="audio/webm",
    language="en",
    name="x",
)
print(response.id)

200 example

{
  "id": "id",
  "cartesiaVoiceId": "cartesiaVoiceId",
  "createdAt": "createdAt",
  "language": "language",
  "name": "name"
}

Returns Examples

200 example

{
  "id": "id",
  "cartesiaVoiceId": "cartesiaVoiceId",
  "createdAt": "createdAt",
  "language": "language",
  "name": "name"
}