Transcribe audio
Amazon Transcribe
AWS speech-to-text service that transcribes audio files from S3 or live streams into JSON transcripts with timestamps.
Rate limits
| Operation | Default per second per region | Adjustable |
|---|---|---|
StartTranscriptionJob | 25 | Yes |
GetTranscriptionJob | 30 | Yes |
ListTranscriptionJobs | 5 | Yes |
DeleteTranscriptionJob | 5 | Yes |
StartStreamTranscription | 25 | Yes |
StartStreamTranscriptionWebSocket | 25 | Yes |
Source8Amazon Transcribe endpoints and quotas
Other limits
- Concurrent batch jobs
- 250 per region (adjustable)8
- Concurrent streams
- 25 per region (adjustable)8
- Maximum audio file length
- 28,800 seconds (8 hours); Call Analytics batch 14,400 seconds8
- Maximum audio file size
- 2 GB; Call Analytics batch 500 MB8
- Minimum audio file duration
- 500 milliseconds8
- Audio channels
- 28
- Streaming connection length
- Up to 8 hours9
Read from Amazon Web Services (AWS)’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/amazon-transcribe.md