Interface: TranscriptionOptions<TProviderOptions>#
Defined in: packages/typescript/ai/src/types.ts:1664
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;
Defined in: packages/typescript/ai/src/types.ts:1670
The audio data to transcribe - can be base64 string, File, Blob, or Buffer
language?#
optional language: string;
Defined in: packages/typescript/ai/src/types.ts:1672
The language of the audio in ISO-639-1 format (e.g., 'en')
logger#
logger: InternalLogger;
Defined in: packages/typescript/ai/src/types.ts:1684
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;
Defined in: packages/typescript/ai/src/types.ts:1668
The model to use for transcription
modelOptions?#
optional modelOptions: TProviderOptions;
Defined in: packages/typescript/ai/src/types.ts:1678
Model-specific options for transcription
prompt?#
optional prompt: string;
Defined in: packages/typescript/ai/src/types.ts:1674
An optional prompt to guide the transcription
responseFormat?#
optional responseFormat: "text" | "json" | "srt" | "verbose_json" | "vtt";
Defined in: packages/typescript/ai/src/types.ts:1676
The format of the transcription output