## Clone

`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.

### Parameters

- `audio: str`

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

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

  MIME type of the audio

  - `"audio/webm"`

  - `"audio/wav"`

  - `"audio/mpeg"`

  - `"audio/ogg"`

  - `"audio/mp4"`

  - `"video/webm"`

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

  Language of the voice

  - `"en"`

  - `"fr"`

  - `"es"`

  - `"de"`

  - `"it"`

  - `"pt"`

  - `"ru"`

  - `"zh"`

- `name: str`

  Name for the cloned voice

### Returns

- `class VoiceCloneResponse: …`

  - `id: str`

  - `cartesia_voice_id: str`

  - `created_at: str`

  - `language: str`

  - `name: str`

### Example

```python
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)
```