R

ryfter/youtube-transcripts

Copy page

Fetch YouTube video transcripts as plain text from Kiro, so the agent can read, summarize, quote, or research spoken video content it otherwise cannot see. Bundles a small Python script that wraps the youtube-transcript-api library: pass one or more video URLs or IDs and it writes one UTF-8 .txt per video, reporting word counts and skipping videos with no captions. Handles full watch URLs, youtu.be short links, /shorts/ and /embed/ forms, and bare 11-character IDs, and works across both the modern (>=1.0) and legacy youtube-transcript-api interfaces. Use when the user shares YouTube links and wants the words, not the video. No API key required; transcripts are pulled from YouTube's public caption tracks.