Video Transcript Downloader
SkillFiles & storageThis skill lets your AI take a video link and pull its subtitles as clean, readable text, or download the video, audio, or subtitle files for you. It strips out timestamps and noise markers and formats the result into tidy paragraphs, so the text is ready to edit or repurpose.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, paste a video link into your chat and ask for a transcript, subtitles, or a download. For text you can work with right away, request the cleaned paragraph version.
Then ask your AI: use the Video Transcript Downloader skill
What your AI can do with it
- Turn a video URL into a plain-text transcript
- Extract subtitles from video websites
- Download the video, audio, or subtitle files
- Remove timestamps and noise markers from subtitles
- Reformat subtitles into clean, paragraph-style text
What this skill tells your AI
The instructions your AI receives, as published by anbeime/skill in skills/video-transcript-downloader/video-transcript-downloader/SKILL.md and read by ahel’s review.
./scripts/vtd.js can:
- Print a transcript as a clean paragraph (timestamps optional).
- Download video/audio/subtitles.
Transcript behavior:
- YouTube: fetch via
youtube-transcript-pluswhen possible. - Otherwise: pull subtitles via
yt-dlp, then clean into a paragraph.
Setup
cd ~/Projects/agent-scripts/skills/video-transcript-downloader && npm ci
Transcript (default: clean paragraph)
./scripts/vtd.js transcript --url 'https://…'
./scripts/vtd.js transcript --url 'https://…' --lang en
./scripts/vtd.js transcript --url 'https://…' --timestamps
./scripts/vtd.js transcript --url 'https://…' --keep-brackets
Download video / audio / subtitles
./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads
./scripts/vtd.js audio --url 'https://…' --output-dir ~/Downloads
./scripts/vtd.js subs --url 'https://…' --output-dir ~/Downloads --lang en
Formats (list + choose)
List available formats (format ids, resolution, container, audio-only, etc):
./scripts/vtd.js formats --url 'https://…'
Download a specific format id (example):
./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --format 137+140
Prefer MP4 container without re-encoding (remux when possible):
./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --remux-video mp4
Notes
- Default transcript output is a single paragraph. Use
--timestampsonly when asked. - Bracketed cues like
[Music]are stripped by default; keep them via--keep-brackets. - Pass extra
yt-dlpargs after--fortranscriptfallback,download,audio,subs,formats.
./scripts/vtd.js formats --url 'https://…' -- -v
Troubleshooting (only when needed)
- Missing
yt-dlp/ffmpeg:
brew install yt-dlp ffmpeg
- Verify:
yt-dlp --version
ffmpeg -version | head -n 1
Signals
- GitHub stars
- 7k
- Forks
- 628
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
video-transcript-downloader- Source
- github.com/anbeime/skill