Transcribe audio
POST/transcriptions
Transcribes an audio file to text using the configured Speech-to-Text provider (OpenAI Whisper, Google Speech-to-Text, or AWS Transcribe). Results are cached by content hash. Optionally post-processes the transcribed text through an LLM.
Request
Responses
- 200
- 400
- 401
- 500
Transcription completed successfully
Invalid or unsupported audio file
Authentication required — provide a valid Bearer token
An unexpected error occurred