Transcribe audio
The transcription layer on its own. Send an audio file, get back the full text and timestamped, speaker-diarized segments in one synchronous response.
The response is synchronous — long recordings are chunked server-side, but expect the request to take roughly a tenth of the audio’s duration. If you also want the document drafted, use POST /uploads instead: same body, full pipeline.
Authorizations
Sign in from your terminal with the OAuth device flow (see the Authentication page for a copy-paste block), or grab your current session token from https://console.silmo.ai/api/auth/token while signed in to the console. Access tokens are short-lived (a few minutes) — refresh with your refresh_token. Everything a session produces is stored and served strictly within your organization's namespace.
Query Parameters
Transcription engine. Defaults to the diarizing OpenAI engine. openai-whisper has no diarization; elevenlabs-scribe is diarized with word timestamps.
openai-diarize, openai-whisper, elevenlabs-scribe Optional name used for format detection on ambiguous content types.
Body
The raw audio file, up to 25 MB, with the matching Content-Type header.
The body is of type file.