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

# Eleven v3

> Expressive text to speech with measured character billing.

Expressive text to speech with measured character billing.

## Model ID

```text theme={"dark"}
eleven_v3
```

Pass this exact public ID in the top-level `model` field.

## Supported modes

* `text_to_speech`
* `text_to_dialogue`

## Inputs

* `Text`

## Outputs

* `Audio`

## Capabilities

* `text_to_speech`
* `text_to_dialogue`

### Additional capabilities

* `Speech generation`
* `HTTP audio streaming`
* `Complete-turn WebSocket`

## Technical details

| Property | Value |
| - | - |
| Model family | `ElevenLabs` |
| Modality | `audio` |
| Processing | `Synchronous, streaming, asynchronous task and complete-turn WebSocket` |
| Endpoint | `/api/gengen/v1/audio/generations` |
| Streaming | `HTTP audio and complete-turn WebSocket` |

<Note>
  Availability and final customer prices can change. Check the [Dashboard model catalog](https://gengen.farm/dashboard?section=models) before production use.
</Note>

See the [Audio API guide](/api-reference/elevenlabs/overview) for voice selection, formats, metering, callbacks and WebSocket sessions. Maximum 2,000 characters per generation.

Try [Eleven v3 in API Explorer](https://gengen.farm/api-explorer/demos/audio-generation?model=eleven_v3).

See the [API reference overview](/api-reference/introduction) for authentication, request conventions, and response schemas.


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