> ## Documentation Index
> Fetch the complete documentation index at: https://docs.medera.info/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart — Transcription

> Speech to text from a pre-recorded audio file

Batch transcription for pre-recorded audio.

```bash theme={"system"}
curl -X POST https://api.medera.info/api/transcribe/batch \
  -H "Authorization: Bearer $TOKEN" \
  -F "audio=@recording.wav" \
  -F "language=en-US" \
  -F "diarization=true"

```

Returns a `job_id`. Poll `/api/transcribe/batch/{job_id}` until `status=completed`, then retrieve the transcript at `/api/transcribe/batch/{job_id}/transcript`.

Supports WAV, MP3, M4A, OGG, FLAC up to 150 MB and 60 minutes.