youtube-transcript-yt-dlpExtract YouTube video transcripts from existing captions (manual or auto-generated) using yt-dlp, with optional timestamps and local SQLite caching. Use when...
Install via ClawdBot CLI:
clawdbot install ItzSubhadip/youtube-transcript-yt-dlpThis skill extracts transcripts from existing YouTube captions.
Primary behavior
--text)Reliability behavior
yt-dlp reports no captions for a video, the script tries a fallback: 1) YouTubeβs transcript panel (youtubei get_transcript) when accessible
This published version intentionally does not call third-party transcript providers.
Privacy note: This published version only contacts YouTube directly (via yt-dlp and the transcript panel fallback). It does not send video IDs/URLs to third-party transcript providers.
Cookies: Cookies are treated as secrets.
--cookies / YT_TRANSCRIPT_COOKIES, but does not auto-load cookies from inside the skill directory.~/.config/yt-transcript/.Path safety: This skill restricts --cookies and --cache paths to approved directories.
~/.config/yt-transcript/{baseDir}/cache/ and ~/.config/yt-transcript/Script path:
{baseDir}/scripts/yt_transcript.pyTypical usage:
python3 {baseDir}/scripts/yt_transcript.py python3 {baseDir}/scripts/yt_transcript.py --lang en python3 {baseDir}/scripts/yt_transcript.py --text python3 {baseDir}/scripts/yt_transcript.py --no-ts Cookies (optional, but often required on VPS IPs):
python3 {baseDir}/scripts/yt_transcript.py --cookies /path/to/youtube-cookies.txt YT_TRANSCRIPT_COOKIES=/path/to/youtube-cookies.txtPublishing safety note: Cookies are optional, so YT_TRANSCRIPT_COOKIES is intentionally not required by skill metadata. Only set it if you need authenticated access.
Best practice: store cookies outside the skill folder (so you never accidentally publish them), e.g. ~/.config/yt-transcript/youtube-cookies.txt, and point to it via --cookies or YT_TRANSCRIPT_COOKIES.
A JSON object:
video_id: 11-char idlang: chosen languagesource: manual | auto | panelsegments: list of { start, duration, text } (or text-only when --no-ts)--text)A newline-separated transcript.
[12.34s].--no-ts to output only the text lines.Default cache DB:
{baseDir}/cache/transcripts.sqliteCache key includes:
video_id, lang, source, include_timestamp, formatRecommended local path (ignored by git/publish):
{baseDir}/cache/youtube-cookies.txt (chmod 600)yt-dlp is missing, instruct the user to install it (recommended):pipx install yt-dlpyt-dlp is on PATHGenerated Mar 1, 2026
Instructors and researchers extract transcripts from educational YouTube videos to create study guides, analyze teaching methods, or generate searchable text for academic papers. This skill supports multiple languages and caching for efficient batch processing of video series.
Bloggers and digital marketers use transcripts to repurpose video content into articles, improve SEO with keyword-rich text, and ensure accessibility with subtitles. The local caching speeds up repeated access for editing and analysis.
Organizations audit YouTube videos for regulatory compliance by extracting captions to verify accuracy, ensure accessibility standards (e.g., WCAG), and document content for legal or training purposes. The skill prioritizes manual subtitles for reliability.
Language learners and translators extract transcripts to create subtitles in different languages, analyze speech patterns, or build vocabulary lists. The fallback to auto-generated captions ensures availability even when manual subtitles are missing.
Businesses monitor competitor YouTube channels by extracting transcripts to analyze messaging trends, track product mentions, and generate reports. The optional cookie support helps bypass bot checks on VPS servers for continuous access.
Offer a cloud-based platform where users submit YouTube links to receive formatted transcripts via API, with features like bulk processing, translation, and analytics. Revenue comes from subscription tiers based on usage volume and advanced features.
Provide custom integrations of this skill into existing workflows (e.g., LMS platforms, content management systems) and consulting services for setup, cookie management, and optimization. Revenue is generated through project-based fees and ongoing support contracts.
Aggregate anonymized transcript data from public YouTube videos to sell insights on trends, sentiment analysis, or keyword tracking to marketers and researchers. Ensure privacy by avoiding third-party providers and focusing on publicly accessible content.
π¬ Integration Tip
Ensure yt-dlp is installed via pipx for isolated dependencies, and store cookies in ~/.config/yt-transcript/ to maintain security and avoid accidental publishing.
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp. Use when the user provides a video URL and wants to download it, extract audio (MP3), download subtitles, or select video quality. Triggers on phrases like "δΈθ½½θ§ι’", "download video", "yt-dlp", "YouTube", "Bη«", "ζι³", "ζει³ι’", "extract audio".
Search and add movies to Radarr. Supports collections, search-on-add option.
Control Spotify playback on macOS. Play/pause, skip tracks, control volume, play artists/albums/playlists. Use when a user asks to play music, control Spotify, change songs, or adjust Spotify volume.
Search and add TV shows to Sonarr. Supports monitor options, search-on-add.