v2

latestOpenAPI 3.1.02026-08-01302833.9 KB

Unified Agent APIs

Unified Stt

Unified speech-to-text (batch mode).

Transcribes pre-recorded audio to text. Provide either a URL to the audio file or base64-encoded audio data. Returns transcript with confidence scores and word-level timing.

For real-time streaming transcription, use the WebSocket endpoint at /speech/ws/{session_id} (create session via POST /speech/start_session).

post/v1/speech/transcribe

Request body

audio_urlstring nullable

audio_base64string nullable

languagestring

Response

Successful Response

{"stackTrail":"paths:/v1/speech/transcribe:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}