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

# SpeechRequest

Text-to-speech request input

## Example Usage

```typescript theme={null}
import { SpeechRequest } from "@openrouter/sdk/models";

let value: SpeechRequest = {
  input: "Hello world",
  model: "mistralai/voxtral-mini-tts-2603",
};
```

## Fields

| Field             | Type                                                                            | Required             | Description                                                                                                                                                                                                          | Example                                                                                                                                                                                                                     |
| ----------------- | ------------------------------------------------------------------------------- | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `input`           | *string*                                                                        | :heavy\_check\_mark: | Text to synthesize                                                                                                                                                                                                   | Hello world                                                                                                                                                                                                                 |
| `inputReferences` | *models.SpeechInputReference*\[]                                                | :heavy\_minus\_sign: | Reference content for stateless voice cloning: one `input_audio` part carrying the voice sample, optionally accompanied by one `text` part with its transcript. Only routed to endpoints that support voice cloning. | \[<br />\{<br />"input\_audio": \{<br />"data": "data:audio/wav;base64,UklGRuQXDABXQVZF..."<br />},<br />"type": "input\_audio"<br />},<br />\{<br />"text": "I used to rule the world.",<br />"type": "text"<br />}<br />] |
| `model`           | *string*                                                                        | :heavy\_check\_mark: | TTS model identifier                                                                                                                                                                                                 | mistralai/voxtral-mini-tts-2603                                                                                                                                                                                             |
| `provider`        | [models.SpeechRequestProvider](../models/speechrequestprovider.mdx)             | :heavy\_minus\_sign: | Provider-specific passthrough configuration                                                                                                                                                                          |                                                                                                                                                                                                                             |
| `responseFormat`  | [models.SpeechRequestResponseFormat](../models/speechrequestresponseformat.mdx) | :heavy\_minus\_sign: | Audio output format                                                                                                                                                                                                  | pcm                                                                                                                                                                                                                         |
| `speed`           | *number*                                                                        | :heavy\_minus\_sign: | Playback speed multiplier. Only used by models that support it (e.g. OpenAI TTS). Ignored by other providers.                                                                                                        | 1                                                                                                                                                                                                                           |
| `voice`           | *string*                                                                        | :heavy\_minus\_sign: | Voice identifier (provider-specific).                                                                                                                                                                                | en\_paul\_neutral                                                                                                                                                                                                           |