Speech
Speech to text
Transcribe recorded audio in the background, or stream audio for live transcripts.
4 endpoints
- POSTTranscribe an audio file/api/ext/stt/async-transcribeQueue a long audio file (up to 2 hours) for background transcription.
- GETGet transcription job/api/ext/stt/jobs/{job_id}Get one async transcription job by ID.
- GETList transcription jobs/api/ext/stt/jobsList the async transcription jobs that belong to the project tied to your API key.
- WSStream speech to text/api/ext/stt/wsStream audio over a WebSocket and receive live transcription.
