Interface: TTSOptions<TProviderOptions>#

Defined in: packages/ai/src/types.ts:2229

Options for text-to-speech generation. These are the common options supported across providers.

Type Parameters#

TProviderOptions#

TProviderOptions extends object = object

Properties#

abortSignal?#

optional abortSignal?: AbortSignal;

Defined in: packages/ai/src/types.ts:2253

Effective abort signal composed by the activity from caller abortSignal and/or timeout. Adapters should forward this to the provider SDK when supported. Request-specific — never store on a global client config.

format?#

optional format?: "mp3" | "opus" | "aac" | "flac" | "wav" | "pcm";

Defined in: packages/ai/src/types.ts:2237

The output audio format

logger#

logger: InternalLogger;

Defined in: packages/ai/src/types.ts:2247

Internal logger threaded from the generateSpeech() entry point. Adapters must call logger.request() before the SDK call and logger.errors() in catch blocks.

model#

model: string;

Defined in: packages/ai/src/types.ts:2231

The model to use for TTS generation

modelOptions?#

optional modelOptions?: TProviderOptions;

Defined in: packages/ai/src/types.ts:2241

Model-specific options for TTS generation

speed?#

optional speed?: number;

Defined in: packages/ai/src/types.ts:2239

The speed of the generated audio (0.25 to 4.0)

text#

text: string;

Defined in: packages/ai/src/types.ts:2233

The text to convert to speech

voice?#

optional voice?: string;

Defined in: packages/ai/src/types.ts:2235

The voice to use for generation