# Speech to text API

Transcribe recorded audio in the background, or stream audio for live transcripts.

- [Transcribe an audio file](https://www.nabrah.ai/en/docs/api-reference/speech-to-text/transcribe-an-audio-file.md) `POST /api/ext/stt/async-transcribe`: Queue a long audio file (up to 2 hours) for background transcription.
- [Get transcription job](https://www.nabrah.ai/en/docs/api-reference/speech-to-text/get-transcription-job.md) `GET /api/ext/stt/jobs/{job_id}`: Get one async transcription job by ID.
- [List transcription jobs](https://www.nabrah.ai/en/docs/api-reference/speech-to-text/list-transcription-jobs.md) `GET /api/ext/stt/jobs`: List the async transcription jobs that belong to the project tied to your API key.
- [Stream speech to text](https://www.nabrah.ai/en/docs/api-reference/speech-to-text/stream-speech-to-text.md) `WS /api/ext/stt/ws`: Stream audio over a WebSocket and receive live transcription.