transcript_speakers
List every speaker in a transcript with cue counts, word counts, speaking time, and first/last timestamps, and optionally run diarization to detect speakers when labels are missing.
Instructions
List all speakers in the transcript with cue count, word count, speaking duration, and first/last timestamp. Pass detect: true to run lightweight acoustic + conversational turn diarization when subtitles do not already carry speaker labels.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "transcript_speakers"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file | No | Optional path to a video or subtitle file; defaults to the playing file | |
| count | No | Target number of speakers when detect=true (2-8) | |
| detect | No | Run automatic speaker diarization if true (default false) |