model gateway
Transcribe
Changed onThe desk's ears (2026-10-05): a recording's words, for senses.listen / watch.
Gemini was the only reader of audio and video and it was retired, so a desk sent a walkthrough video could see its frames and hear nothing. The body is the raw audio; X-Stormy-Audio-Context is one line about what it is. The transcription model is the deployment's declared one, metered and charged like every other call — the senses token may use it, since hearing a file is reading it.
post/v1/teams/{team_id}/model-gateway/audio/transcribe
Request
- Base URL: https://api.stormy.ai (the document declares no server; this is the origin it was published from)
- URL: https://api.stormy.ai/v1/teams/{team_id}/model-gateway/audio/transcribe
- Auth: none declared
Path parameters
team_idstring uuid required
Headers
authorizationstring nullable
x-darwin-tokenstring nullable
x-darwin-run-idstring nullable
Response
Successful Response
unknown required
Changes
- info
endpoint added
- info