ryfter/youtube-transcripts

v1.0.0MIT

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.

GitHub Open Website

skills

fetch-transcripts

Fetch YouTube video transcripts as plain text so the agent can read, summarize, quote, or research spoken video content. Runs a bundled Python script (wrapping youtube-transcript-api) against one or more video URLs or IDs and writes one .txt per video. Use when the user shares YouTube links or IDs and wants the words rather than the video — for research, summaries, quotes, or slide/content prep.

Version: 1.0.0
License: MIT
Compatibility: Requires Python 3.8+ and the youtube-transcript-api package (pip install youtube-transcript-api). No API key needed.

Read SKILL.md at the source

Pinned to revision e3ecc05222da, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.