STTRequest

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

Fields

Field	Type	Required	Description	Example
`InputAudio`	components.STTInputAudio	:heavy_check_mark:	Base64-encoded audio to transcribe	{ “data”: “UklGRiQA…”, “format”: “wav” }
`Language`	`*string`	:heavy_minus_sign:	ISO-639-1 language code (e.g., “en”, “ja”). Auto-detected if omitted.	en
`Model`	`string`	:heavy_check_mark:	STT model identifier	openai/whisper-large-v3
`Provider`	*components.STTRequestProvider	:heavy_minus_sign:	Provider-specific passthrough configuration
`ResponseFormat`	*components.STTRequestResponseFormat	:heavy_minus_sign:	Output format. “json” (default) returns { text, usage }. “verbose_json” additionally returns task, language, duration, and segment-level timestamps; only supported by OpenAI-compatible providers.	json
`Temperature`	`*float64`	:heavy_minus_sign:	Sampling temperature for transcription	0
`TimestampGranularities`	[]components.STTTimestampGranularity	:heavy_minus_sign:	Timestamp detail levels to include when response_format is “verbose_json”. “segment” returns segment-level timestamps; “word” additionally returns word-level timestamps in the words array. Ignored unless response_format is “verbose_json”.	[ “segment” ]

⌘I