transcribe_file
Transcribes audio files (mp3, wav, m4a, etc.) to text with optional language auto-detection and GPT post-processing for grammar and spelling correction.
Instructions
Transcribe an audio file to text.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Absolute path to the audio file (mp3, wav, m4a, ogg, flac, etc.) | |
| language | No | Language code (e.g. 'es', 'en', 'fr'). Auto-detected if not provided. | |
| model_size | No | Local model size: tiny, base, small, medium, large-v3. Ignored when using the OpenAI backend. Defaults to the WHISPER_MODEL environment variable (default: 'base'). | |
| post_process | No | If True, passes the transcription through GPT to fix spelling, grammar, and punctuation. Requires the openai package. | |
| post_process_prompt | No | Custom system prompt for post-processing. Use this to provide domain-specific context, proper nouns, or product names that Whisper may have misspelled. Falls back to a generic correction prompt if not provided. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||