> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Eleven v4 Voice Clone

> Speak text in a voice cloned from samples

> [card] [Try Eleven v4 Voice Clone in the Workbench](https://www.oxen.ai/ai/workbench?model=elevenlabs-eleven-v4-voice-clone)
>
> Run this model interactively, tune parameters, and compare outputs.

**Model ID:** `elevenlabs-eleven-v4-voice-clone`

Eleven v4 Voice Clone speaks your text in a voice cloned from short reference recordings, with Eleven v4's expressive delivery across more than 90 languages.

Upload one or more clean clips of the speaker along with the text to say, and the model speaks it in that voice. Audio tags such as `[whispering]` or `[laughing]` direct delivery as with Eleven v4, and the clone can speak languages the reference never did. More and cleaner reference audio, a minute or two in total without music or other voices, gives a closer match. You must have the right to use the voice you upload.

| Metric | Value |
| - | - |
| Context Length | 10,000 characters |
| Multilingual | Yes, 90+ languages |

## Example request

> [!TIP]
>
> Use the [Workbench](https://www.oxen.ai/ai/workbench?model=elevenlabs-eleven-v4-voice-clone) as a request builder: configure parameters for this model in the UI, then open the **API** tab to copy the exact cURL or Python call.

> [tab] Minimal
>
> ```bash cURL theme={null}
> curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
>   -H "Content-Type: application/json" \
>   -H "Authorization: Bearer $OXEN_API_KEY" \
>   -d '{
>   "model": "elevenlabs-eleven-v4-voice-clone",
>   "prompt": "<prompt>",
>   "input_audios": [
>     "https://example.com/audio.mp3"
>   ],
>   "voice_rights_confirmed": false,
>   "input": "Welcome to Oxen"
> }'
> ```
>
> ```python Python theme={null}
> import os
> import requests
>
> response = requests.post(
>     "https://hub.oxen.ai/api/ai/audio/speech",
>     headers={
>         "Content-Type": "application/json",
>         "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
>     },
>     json={
>         "model": "elevenlabs-eleven-v4-voice-clone",
>         "prompt": "<prompt>",
>         "input_audios": [
>             "https://example.com/audio.mp3"
>         ],
>         "voice_rights_confirmed": false,
>         "input": "Welcome to Oxen"
>     },
> )
> response.raise_for_status()
> print(response.json())
> ```

> [tab] All parameters
>
> ```bash cURL theme={null}
> curl -X POST https://hub.oxen.ai/api/ai/audio/speech \
>   -H "Content-Type: application/json" \
>   -H "Authorization: Bearer $OXEN_API_KEY" \
>   -d '{
>   "model": "elevenlabs-eleven-v4-voice-clone",
>   "prompt": "<prompt>",
>   "input_audios": [
>     "https://example.com/audio.mp3"
>   ],
>   "voice_rights_confirmed": false,
>   "remove_background_noise": false,
>   "stability": 0.5,
>   "similarity_boost": 0.75,
>   "input": "Welcome to Oxen"
> }'
> ```
>
> ```python Python theme={null}
> import os
> import requests
>
> response = requests.post(
>     "https://hub.oxen.ai/api/ai/audio/speech",
>     headers={
>         "Content-Type": "application/json",
>         "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
>     },
>     json={
>         "model": "elevenlabs-eleven-v4-voice-clone",
>         "prompt": "<prompt>",
>         "input_audios": [
>             "https://example.com/audio.mp3"
>         ],
>         "voice_rights_confirmed": false,
>         "remove_background_noise": false,
>         "stability": 0.5,
>         "similarity_boost": 0.75,
>         "input": "Welcome to Oxen"
>     },
> )
> response.raise_for_status()
> print(response.json())
> ```

## Fetch model details

The [models endpoint](https://docs.oxen.ai/inference-api/reference/models/overview.md) returns the full model object, including its `json_request_schema`.

```bash theme={null}
curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/elevenlabs-eleven-v4-voice-clone
```

## Request parameters

### Required parameters

| Field | Type | Default | Description |
| - | - | - | - |
| `prompt` | `string` | — | Text to speak, up to 10,000 characters. Put audio tags in square brackets before a line to direct its delivery, e.g. \[whispering], \[excited]. |
| `input_audios` | `array<string>` | — | Clean recordings of the voice to clone, up to 5 clips. A minute or two in total, without music or other speakers, works best. |
| `voice_rights_confirmed` | `boolean` | `false` | I confirm I have the rights and consent to clone this voice. |

### Optional parameters

| Field | Type | Default | Description |
| - | - | - | - |
| `remove_background_noise` | `boolean` | `false` | Clean background noise from the samples before cloning. Can lower quality on samples that are already clean. |
| `language_code` | `string` | — | Optional ISO 639-1 language code (e.g. en, es, ja) to force the language and its text normalization. Leave empty to detect it from the text. |
| `stability` | `number` | `0.5` | Lower values give more varied, expressive delivery; higher values keep the performance consistent across generations. Range: 0.0 – 1.0. |
| `similarity_boost` | `number` | `0.75` | How closely the output follows the cloned voice. Higher values match it more closely at some cost to naturalness. Range: 0.0 – 1.0. |
| `seed` | `integer` | — | Optional seed for best-effort deterministic output. Range: 0 – 4294967295. |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.