> Documentation index: https://firebase.google.com/docs/reference/js/llms.txt

> This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Structured speech metadata associated with a [TextPart](https://firebase.google.com/docs/reference/js/ai.textpart.md.txt#textpart_interface).

Used to guide speech generation for a specific piece of text, such as identifying which speaker says it and the vocal style they should use.

**Signature:**

```typescript
export interface SpeechMetadata 
```

## Properties

| Property | Type | Description |
|---|---|---|
| [speaker](https://firebase.google.com/docs/reference/js/ai.speechmetadata.md.txt#speechmetadataspeaker) | string | ***(Public Preview)*** Identifies which speaker is speaking this turn. When using a [MultiSpeakerVoiceConfig](https://firebase.google.com/docs/reference/js/ai.multispeakervoiceconfig.md.txt#multispeakervoiceconfig_interface), this should match the [SpeakerVoiceConfig.speaker](https://firebase.google.com/docs/reference/js/ai.speakervoiceconfig.md.txt#speakervoiceconfigspeaker) of one of the configured speakers. |
| [style](https://firebase.google.com/docs/reference/js/ai.speechmetadata.md.txt#speechmetadatastyle) | string | ***(Public Preview)*** A natural language description of the vocal style (such as `"cheerful"`). |

## SpeechMetadata.speaker

> This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

Identifies which speaker is speaking this turn. When using a [MultiSpeakerVoiceConfig](https://firebase.google.com/docs/reference/js/ai.multispeakervoiceconfig.md.txt#multispeakervoiceconfig_interface), this should match the [SpeakerVoiceConfig.speaker](https://firebase.google.com/docs/reference/js/ai.speakervoiceconfig.md.txt#speakervoiceconfigspeaker) of one of the configured speakers.

**Signature:**

```typescript
speaker?: string;
```

## SpeechMetadata.style

> This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.

A natural language description of the vocal style (such as `"cheerful"`).

**Signature:**

```typescript
style?: string;
```