TTSResult

Defined in: packages/ai/src/types.ts:2976

Result of text-to-speech generation.

Properties#

alignment?#

optional alignment?: TTSAlignment;

Defined in: packages/ai/src/types.ts:2991

Character- or word-level timings, present when timestamps: true was requested. Use this rather than duration to find where speech ends.

artifacts?#

optional artifacts?: PersistedArtifactRef[];

Defined in: packages/ai/src/types.ts:3002

Persisted artifact references for generated assets, when available

audio#

audio: string;

Defined in: packages/ai/src/types.ts:2982

Base64-encoded audio data

contentType?#

optional contentType?: string;

Defined in: packages/ai/src/types.ts:2998

Content type of the audio (e.g., 'audio/mp3')

duration?#

optional duration?: number;

Defined in: packages/ai/src/types.ts:2986

Duration of the audio file in seconds, if available

format#

format: string;

Defined in: packages/ai/src/types.ts:2984

Audio format of the generated audio

id#

id: string;

Defined in: packages/ai/src/types.ts:2978

Unique identifier for the generation

model#

model: string;

Defined in: packages/ai/src/types.ts:2980

Model used for generation

segments?#

optional segments?: TTSSegment[];

Defined in: packages/ai/src/types.ts:2996

Per-turn (or per-utterance) spans of the audio, present when timestamps: true was requested and the provider reports segmentation.

usage?#

optional usage?: TokenUsage<ProviderUsageDetails>;

Defined in: packages/ai/src/types.ts:3000

Token usage information (if provided by the adapter)