要点
Download YouTube transcripts, subtitles, and cover images with multi-language support and intelligent caching.
- Accepts YouTube URLs or video IDs in multiple formats; no API key required, uses InnerTube API with automatic fallback to
yt-dlpwhen blocked - Outputs markdown with timestamps, SRT subtitles, or raw transcript; supports language selection, translation, chapter segmentation, and speaker identification via AI post-processing
- Caches raw transcript data and metadata on first fetch for fast re-formatting without network calls; use
--refreshto force re-fetch - Handles CJK text intelligently, proportionally allocates timestamps across sentence boundaries, and auto-generates cover images and video metadata
SKILL.md
YouTube Transcript
Downloads transcripts (subtitles/captions) from YouTube videos. Works with both manually created and auto-generated transcripts. No API key or browser required — uses YouTube's InnerTube API directly and automatically falls back to yt-dlp when YouTube blocks the direct API path.
Fetches video metadata and cover image on first run, caches raw data for fast re-formatting.
Script Directory
Scripts in scripts/ subdirectory. {baseDir} = this SKILL.md's directory path. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun. Replace {baseDir} and ${BUN_X} with actual values.
| Script | Purpose |
|---|---|
scripts/main.ts |
Transcript download CLI |
Usage
# Default: markdown with timestamps (English)
${BUN_X} {baseDir}/scripts/main.ts <youtube-url-or-id>