get_timed_transcript
Fetch timestamped YouTube transcript in JSON, SRT, VTT, CSV, or TXT format. Preprocess captions by filtering empty segments, merging overlaps, or removing silences.
Instructions
Returns timestamped transcript segments in multiple formats (JSON, SRT, VTT, CSV, TXT) with optional preprocessing
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": {
"url": "<url>"
},
"name": "get_timed_transcript"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | YouTube video URL or video ID | |
| lang | No | Language code (default: en) | en |
| format | No | Output format (default: json). Options: 'json' (structured data), 'srt' (SubRip subtitles), 'vtt' (WebVTT captions), 'csv' (spreadsheet), 'txt' (plain text) | json |
| filterEmpty | No | Remove segments with empty or whitespace-only text (default: false). Useful for cleaning auto-generated captions. | |
| mergeOverlaps | No | Merge segments with overlapping timestamps (default: false). Useful for fixing word-level timing issues in auto-generated captions. | |
| removeSilence | No | Remove silence markers like [silence], [pause], [Music] (default: false). More aggressive than filterEmpty. |