Interface: TranscriptionOptions<TProviderOptions>#

Defined in: packages/ai/src/types.ts:1718

Options for audio transcription. These are the common options supported across providers.

Type Parameters#

TProviderOptions#

TProviderOptions extends object = object

Properties#

audio#

audio: string | File | Blob | ArrayBuffer;

audio: string | File | Blob | ArrayBuffer;

Defined in: packages/ai/src/types.ts:1724

The audio data to transcribe - can be base64 string, File, Blob, or Buffer

language?#

optional language: string;

optional language: string;

Defined in: packages/ai/src/types.ts:1726

The language of the audio in ISO-639-1 format (e.g., 'en')

logger#

logger: InternalLogger;

logger: InternalLogger;

Defined in: packages/ai/src/types.ts:1738

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

model#

model: string;

model: string;

Defined in: packages/ai/src/types.ts:1722

The model to use for transcription

modelOptions?#

optional modelOptions: TProviderOptions;

optional modelOptions: TProviderOptions;

Defined in: packages/ai/src/types.ts:1732

Model-specific options for transcription

prompt?#

optional prompt: string;

optional prompt: string;

Defined in: packages/ai/src/types.ts:1728

An optional prompt to guide the transcription

responseFormat?#

optional responseFormat: "text" | "json" | "srt" | "verbose_json" | "vtt";

optional responseFormat: "text" | "json" | "srt" | "verbose_json" | "vtt";

Defined in: packages/ai/src/types.ts:1730

The format of the transcription output