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

# AssemblyAI WebSocket TTS provider

> Configure the AssemblyAI text-to-speech provider for Telnyx WebSocket TTS, including voices, language, audio formats, and sample rates.

> [!NOTE]
>
> This page applies when `provider=assemblyai` — either via the `voice` compound parameter or by setting `provider=assemblyai` explicitly. See [Configuration](https://developers.telnyx.com/docs/voice/tts/websocket-streaming/configuration.md).

## Voice Format

```
AssemblyAI.assemblyai-tts-1.<VoiceId>
```

Example: `AssemblyAI.assemblyai-tts-1.aai-jane`

## Models

| Model | Description |
| - | - |
| `assemblyai-tts-1` | Streaming model. **Default** and the only model accepted. |

## Voices

11 voices under `assemblyai-tts-1`; every voice speaks all six supported languages. The list is on the [AssemblyAI provider page](https://developers.telnyx.com/docs/voice/tts/providers/assemblyai.md), or browse it via the [Voices API](https://developers.telnyx.com/api-reference/text-to-speech-commands/list-available-voices.md).

## Language

Set `voice_settings.language` on the init frame, or the `language` query parameter, to the two-letter ISO 639-1 code of the text: `en`, `es`, `de`, `fr`, `it`, or `pt`. The default is `en`. AssemblyAI does not detect the language, and any other language is rejected with an error.

## Voice Settings

| Field | Type | Default | Description |
| - | - | - | - |
| `language` | string | `en` | Two-letter ISO 639-1 code of the text. |

```json theme={null}
{
  "text": " ",
  "voice_settings": {
    "language": "fr"
  }
}
```

SSML is not supported, and there are no speed, pitch, or emotion controls. Send plain text.

## Audio Output

Streamed delivery. Default: MP3 at 24 kHz. Use the `audio_format` and `sample_rate` query parameters to change the output:

| `audio_format` | Accepted Sample Rates (Hz) | Default |
| - | - | - |
| `mp3` | 8000, 16000, 22050, 24000, 44100, 48000 | 24000 |
| `wav` | 8000, 16000, 22050, 24000, 44100, 48000 | 24000 |
| `linear16` | 8000, 16000, 22050, 24000, 44100, 48000 | 24000 |
| `mulaw` | 8000, 16000, 22050, 24000, 44100, 48000 | 8000 |
| `alaw` | 8000, 16000, 22050, 24000, 44100, 48000 | 8000 |

```
wss://api.telnyx.com/v2/text-to-speech/speech?voice=AssemblyAI.assemblyai-tts-1.aai-jane&audio_format=mulaw
```

## Limits

A request accepts up to 5,000 characters. Split longer text into several requests.

AssemblyAI is a third-party provider that synthesizes speech in the United States. Requests that require in-transit data locality are refused. See [Data Residency](https://developers.telnyx.com/docs/inference/data-residency.md).