Python SDKAPI ReferenceComponents

STTRequest - Python SDK

STTRequest method reference

The Python SDK and docs are currently in beta. Report issues on GitHub.

Speech-to-text request input. Accepts a JSON body with input_audio containing base64-encoded audio.

Fields

FieldTypeRequiredDescriptionExample
input_audiocomponents.STTInputAudio✔️Base64-encoded audio to transcribe{"data": "UklGRiQA...","format": "wav"}
languageOptional[str]➖ISO-639-1 language code (e.g., “en”, “ja”). Auto-detected if omitted.en
modelstr✔️STT model identifieropenai/whisper-large-v3
providerOptional[components.STTRequestProvider]➖Provider-specific passthrough configuration
temperatureOptional[float]➖Sampling temperature for transcription0