mistral_transcribe
Transcribe all audio files in a staging session to text, with optional speaker identification and timestamp granularity for structured knowledge extraction.
Instructions
Transcribe all audio files in a staging session.
Uses the session language set via mistral_set_language (default: English).
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": {
"session_id": "<session_id>"
},
"name": "mistral_transcribe"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| diarize | No | Enable speaker identification. | |
| session_id | Yes | The staging session ID. | |
| timestamp_granularity | No | 'segment' or 'word' level timestamps (ignored for non-English). | segment |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |