transcript
Skill15 starsChanged 3 months agoMITView on GitHub
Download or transcribe text from any audio/video source. For YouTube URLs, fetches subtitles (manual preferred, then auto-generated, then Whisper fallback). For any audio/video file, transcribes directly with faster-whisper — generating plain text, SRT/VTT subtitles, JSON, or timestamped segments. Supports batch processing and translation. Trigger keywords: transcribe, transcript, download transcript, get captions, get subtitles, extract text from video, convert audio to text, YouTube transcript, generate subtitles, transcribe podcast, audio to text, video to text.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/amplifier-bundle-context-intelligencetheir own version, first seen Nov 6, 2026
- notegpt-official/notegpt-skillsword for word, first seen Nov 6, 2026
- tandregbg/core-claude-skillstheir own version, first seen Nov 4, 2026
- geekatron/jerrytheir own version, first seen Nov 1, 2026
- qwwiwi/agentos-skills-publictheir own version, first seen Nov 1, 2026
- jantichy/claudetheir own version, first seen Oct 27, 2026
Other versions11 projects use a version of this.
Word for word · 1
- notegpt-official/notegpt-skills★ 16100% same
Edited · 0
None found.
Wrote their own version · 10
- ZeroPointRepo/youtube-skills★ 972same name
- artemchuikin/youtube-skills★ 273same name
- jantichy/claude★ 45same name
- geekatron/jerry★ 37same name
- coopersimson96/ai-content-system★ 17same name
- microsoft/amplifier-bundle-context-intelligence★ 5same name
- qwwiwi/agentos-skills-public★ 4same name
- tandregbg/core-claude-skills★ 4same name
- mrboups/xbrain★ 2same name
- Gopyr/gopyr-skills-hub★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- ai-documentsSkill
- ai-sheetsSkill
- browser-automationSkill
- data-analysisSkill
- deep-researchSkill
- page-seo-checkerSkill
- page-seo-generator-i18nSkill
- page-seo-generatorSkill
- seo-image-generatorSkill
- seo-keyword-difficultySkill
The file
Files
Transcript — Universal Audio/Video to Text
Fetch YouTube transcripts via yt-dlp, or transcribe any audio/video file with OpenAI Whisper.
Routing
User input:
├── YouTube URL? → Read references/youtube-transcript.md and follow its workflow
└── Audio/video file? → Read references/whisper-transcription.md and follow its workflowAlways ask the user before large downloads (audio files, Whisper models). Clean up temporary files when done.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.