AgentSkillsCN

video-transcript-downloader

从 YouTube 及其他支持 yt-dlp 的网站下载视频、音频、字幕，并生成清晰流畅的段落式文字稿。当用户提出“下载这个视频”“保存这段片段”“提取音频”“获取字幕”“生成文字稿”，或需要排查 yt-dlp/ffmpeg 以及各类格式与播放列表的问题时，此技能都能轻松应对。

SKILL.md
--- frontmatter
name: video-transcript-downloader
description: Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Video Transcript Downloader

./scripts/vtd.js can:

  • •Print a transcript as a clean paragraph (timestamps optional).
  • •Download video/audio/subtitles.

Transcript behavior:

  • •YouTube: fetch via youtube-transcript-plus when possible.
  • •Otherwise: pull subtitles via yt-dlp, then clean into a paragraph.

Setup

Run the installation script to set up dependencies (including yt-dlp in a virtual environment):

bash
./install.sh

Or manually:

bash
uv venv
source .venv/bin/activate
uv pip install yt-dlp
pnpm install

Transcript (default: save to ./transcripts)

Transcripts are saved to ./transcripts/YYYY-MM-DD_title-short.md by default.

bash
./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
./scripts/vtd.js transcript --url 'https://…' --no-to-file  # Print to console instead

Search

Search for videos and download transcripts (default limit: 1). Auto-detects "top N" in query. Transcripts are saved to file by default.

bash
./scripts/vtd.js search "top 3 ai videos on reinforcement learning"
./scripts/vtd.js search "nextjs tutorial" --limit 5
./scripts/vtd.js search "..." --no-to-file --timestamps

Download video / audio / subtitles

bash
./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):

bash
./scripts/vtd.js formats --url 'https://…'

Download a specific format id (example):

bash
./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --format 137+140

Prefer MP4 container without re-encoding (remux when possible):

bash
./scripts/vtd.js download --url 'https://…' --output-dir ~/Downloads -- --remux-video mp4

Notes

  • •Default transcript output is a single paragraph. Use --timestamps only when asked.
  • •Bracketed cues like [Music] are stripped by default; keep them via --keep-brackets.
  • •By default, transcripts are saved to ./transcripts/YYYY-MM-DD_title-short.md in the current working directory. Use --no-to-file to print to stdout instead.
  • •Pass extra yt-dlp args after -- for transcript fallback, download, audio, subs, formats.
bash
./scripts/vtd.js formats --url 'https://…' -- -v

Troubleshooting (only when needed)

  • •Missing yt-dlp / ffmpeg:

Run ./install.sh to fix missing yt-dlp. For ffmpeg (required for audio conversion):

bash
brew install ffmpeg
  • •Verify:
bash
./scripts/vtd.js --help