transcribe_audio
Transcribe audio files to text using models like gpt-4o-mini-transcribe or gpt-4o-transcribe. Options include prompts, timestamp granularities, and various output formats.
Instructions
A tool used to transcribe audio files. It is recommended to use gpt-4o-mini-transcribe by default. If the user wants maximum performance, use gpt-4o-transcribe. Rarely should you use whisper-1 as it is least performant, but it is available if needed. You can use prompts to guide the transcription process based on the users preference.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input_file_name | Yes | ||
| model | No | gpt-4o-mini-transcribe | |
| response_format | No | text | |
| prompt | No | ||
| timestamp_granularities | No |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The transcribed text | |
| duration | No | Duration of the audio in seconds | |
| language | No | Detected language of the audio | |
| segments | No | Timestamped segments | |
| words | No | Word-level timestamps | |
| usage | No | Token usage information | |
| logprobs | No | Log probabilities if requested |