transcribe_file
Transcribe local audio or video files to text with whisper.cpp, returning the full transcript and optional timestamped segments for further analysis.
Instructions
Transcribe a local audio/video file with whisper.cpp. Returns the transcript text and optional segments.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"path": "<path>"
},
"name": "transcribe_file"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Local path to the audio/video file. | |
| model | No | Path to a .ggml whisper model, or a name hint. | |
| language | No | Language code: 'en', 'zh', 'auto' (default: auto). | |
| translate | No | Translate non-English speech into English. | |
| timestamps | No | Include [start --> end] segment boundaries. |