start_batch
Begin a sequential batch transcription of untranscribed audio files. Scans folder, sorts by duration, and processes each file individually, with output validation. Returns a batch ID for progress checking.
Instructions
Start an automated sequential batch transcription of all untranscribed files in a folder. Scans for files without a matching .txt, sorts by duration (shortest first), and processes them one at a time as background jobs. Each file is validated after completion — empty or suspiciously short outputs are flagged. Batch self-advances without polling when each file finishes. Returns a batch ID to use with check_batch_progress. ⚠️ Privacy: when privacy_mode is active, one confirmation is required before the batch starts. All files then process unattended. No transcript text is returned to the API.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| folder_path | Yes | Absolute Windows path to the folder. | |
| language | No | Language code. Defaults to en. | en |
| threads | No | CPU threads. Defaults to 2 of 2. | |
| output_format | No | timestamps = with time codes (default), text = plain. Applies to all files in the batch. | timestamps |
| privacy_mode | No | Override privacy mode for this batch. When active, requires one confirmation before batch start. All files process unattended with no transcript text returned. |