> ## 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` | *models.SpeechInput* | ✔️ | Text to synthesize, or a list of turns for multi-speaker input. Each turn has its own text, voice, and instructions. Multi-speaker input is supported by Gemini TTS models and by Fish Audio models other than S1. | Hello world |
| `inputReferences` | *models.SpeechInputReference*\[] | ➖ | Reference content for stateless voice cloning or voice design. Audio mode: one to three `input_audio` parts, each optionally paired with a `text` part carrying its transcript (a single clip accepts its transcript before or after it; with multiple clips each transcript immediately follows its clip), plus at most one `image_url` part as a scene image on providers that condition the cloned voice on its setting; only routed to endpoints that support voice cloning (and multiple references or image references when those parts are sent). Image mode: exactly one `image_url` part; only routed to endpoints that support image references. An empty array is treated as no reference. | \[ \{ "input\_audio": \{ "data": "data:audio/wav;base64,UklGRuQXDABXQVZF..." }, "type": "input\_audio" }, \{ "text": "I used to rule the world.", "type": "text" } ] |
| `instructions` | *string* | ➖ | Delivery instructions for the whole request, such as tone, pacing, or emotion. Supported by OpenAI gpt-4o-mini-tts, Gemini TTS, and Fish Audio models. Ignored by other providers. | Speak in a warm and friendly tone. |
| `model` | *string* | ✔️ | TTS model identifier | mistralai/voxtral-mini-tts-2603 |
| `provider` | [models.SpeechRequestProvider](../models/speechrequestprovider.mdx) | ➖ | Provider configuration: data policy routing preferences (`zdr`, `data_collection`) and provider-specific passthrough options | |
| `responseFormat` | [models.SpeechRequestResponseFormat](../models/speechrequestresponseformat.mdx) | ➖ | Audio output format | pcm |
| `sessionId` | *string* | ➖ | A unique identifier for grouping related requests (e.g., a conversation or agent workflow). Used for observability grouping in Broadcast and private logging; never sent to the provider. If provided in both the request body and the x-session-id header, the body value takes precedence. Maximum of 256 characters. | session-1234 |
| `speed` | *number* | ➖ | Playback speed multiplier. Honored by models that support it (e.g. OpenAI TTS). Other providers either ignore it or return a 400 for a non-default value when the model has no speed control. | 1 |
| `trace` | [models.TraceConfig](../models/traceconfig.mdx) | ➖ | Metadata for observability and tracing. Known keys (trace\_id, trace\_name, span\_name, generation\_name, parent\_span\_id) have special handling. Additional keys are passed through as custom metadata to configured broadcast destinations. | \{ "trace\_id": "trace-abc123", "trace\_name": "my-app-trace" } |
| `user` | *string* | ➖ | A unique identifier representing your end-user. Forwarded to Broadcast and private logging as the end-user id; never sent to the provider. | user-1234 |
| `voice` | *string* | ➖ | Voice identifier (provider-specific). | en\_paul\_neutral |