Youtube Transcript

Name: Youtube Transcript
Author: badlogic

badlogic/pi-skills

248 installs
2.3k repo stars
Updated June 6, 2026
badlogic/pi-skills

Pull YouTube video transcripts for competitive research, tutorial mining, quote extraction, and grounding agent answers in spoken source material.

About

youtube-transcript from badlogic/pi-skills enables agents to retrieve transcript text from YouTube videos for research, summarization, and content reuse. It supports early discovery and ongoing agent workflows that need reliable access to spoken video material.

Extracts YouTube captions and transcripts
Speeds competitive and tutorial research
Grounds agents in video source text
Useful for content repurposing pipelines
Avoids manual copy from video players

Youtube Transcript by the numbers

248 all-time installs (skills.sh)
Ranked #2,575 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/badlogic/pi-skills --skill youtube-transcript

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/badlogic/pi-skills/youtube-transcript.svg)](https://skillselion.com/skills/badlogic/pi-skills/youtube-transcript)

Installs	248
repo stars	★ 2.3k
Last updated	June 6, 2026
Repository	badlogic/pi-skills ↗

What it does

Pull YouTube video transcripts for competitive research, tutorial mining, quote extraction, and grounding agent answers in spoken source material.

Files

SKILL.mdMarkdownGitHub ↗

YouTube Transcript

Fetch transcripts from YouTube videos.

Setup

cd {baseDir}
npm install

Usage

{baseDir}/transcript.js <video-id-or-url>

Accepts video ID or full URL:

EBw7gsDPAYQ
https://www.youtube.com/watch?v=EBw7gsDPAYQ
https://youtu.be/EBw7gsDPAYQ

Output

Timestamped transcript entries:

[0:00] All right. So, I got this UniFi Theta
[0:15] I took the camera out, painted it
[1:23] And here's the final result

Notes

Requires the video to have captions/transcripts available
Works with auto-generated and manual transcripts

#!/usr/bin/env node

import { YoutubeTranscript } from 'youtube-transcript-plus';

const videoId = process.argv[2];

if (!videoId) {
  console.error('Usage: transcript.js <video-id-or-url>');
  console.error('Example: transcript.js EBw7gsDPAYQ');
  console.error('Example: transcript.js https://www.youtube.com/watch?v=EBw7gsDPAYQ');
  process.exit(1);
}

// Extract video ID if full URL is provided
let extractedId = videoId;
if (videoId.includes('youtube.com') || videoId.includes('youtu.be')) {
  const match = videoId.match(/(?:v=|youtu\.be\/)([a-zA-Z0-9_-]{11})/);
  if (match) {
    extractedId = match[1];
  }
}

try {
  const transcript = await YoutubeTranscript.fetchTranscript(extractedId);
  
  for (const entry of transcript) {
    const timestamp = formatTimestamp(entry.offset / 1000);
    console.log(`[${timestamp}] ${entry.text}`);
  }
} catch (error) {
  console.error('Error fetching transcript:', error.message);
  process.exit(1);
}

function formatTimestamp(seconds) {
  const h = Math.floor(seconds / 3600);
  const m = Math.floor((seconds % 3600) / 60);
  const s = Math.floor(seconds % 60);
  
  if (h > 0) {
    return `${h}:${m.toString().padStart(2, '0')}:${s.toString().padStart(2, '0')}`;
  }
  return `${m}:${s.toString().padStart(2, '0')}`;
}