Fields
| Field | Type | Required | Description | Example |
|---|---|---|---|---|
input_audio | components.STTInputAudio | :heavy_check_mark: | Base64-encoded audio to transcribe | {"data": "UklGRiQA...","format": "wav"} |
language | Optional[str] | :heavy_minus_sign: | ISO-639-1 language code (e.g., “en”, “ja”). Auto-detected if omitted. | en |
model | str | :heavy_check_mark: | STT model identifier | openai/whisper-large-v3 |
provider | Optional[components.STTRequestProvider] | :heavy_minus_sign: | Provider-specific passthrough configuration | |
temperature | Optional[float] | :heavy_minus_sign: | Sampling temperature for transcription | 0 |