youtube-transcript

Retrieve YouTube transcripts and captions from video URLs using yt-dlp.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/gupsammy/Claude-setup --skill youtube-transcript-gupsammy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/gupsammy/Claude-setup/tree/main/skills/youtube-transcript
Command: npx skills add https://github.com/gupsammy/Claude-setup --skill youtube-transcript-gupsammy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the retrieval of transcripts and captions from YouTube videos, turning video content into searchable text for summaries, analysis, or archival records.

Core Features & Use Cases

  • Transcript extraction: Fetch available subtitles (manual or auto-generated) or transcribe with Whisper when needed.
  • Versatile outputs: Save as WebVTT or plain text for downstream workflows.
  • Use Case: Convert a collection of YouTube tutorials into a searchable knowledge base.

Quick Start

Use the youtube-transcript skill to download the transcript for a YouTube URL, or extract captions to feed into a summarization pipeline.

Frequently Asked Questions about youtube-transcript

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download YouTube transcripts and captions from video URLs?

To download YouTube transcripts, you automate retrieval using a video URL and yt-dlp to fetch available subtitles. When subtitles are unavailable, it optionally uses Whisper to transcribe the audio directly.

Can I extract auto-generated subtitles as plain text instead of WebVTT?

Yes, you can extract auto-generated subtitles and save them as plain text. The retrieval process supports versatile outputs, allowing you to format downloaded YouTube captions for downstream workflows.

Do I need yt-dlp and Whisper installed to fetch subtitles from YouTube?

You need yt-dlp installed to fetch available manual or auto-generated subtitles from YouTube. Whisper is an optional dependency required only when transcoding audio for videos lacking subtitles.

What is the best way to convert YouTube tutorials into a searchable knowledge base?

The best way to build a searchable knowledge base from YouTube tutorials is automating transcript extraction. This converts video content into searchable text files for summaries and archival records.

Why does YouTube transcript extraction fail for videos without subtitles?

YouTube transcript extraction fails without subtitles because yt-dlp cannot locate text data. In these cases, the system requires optional Whisper transcription to process and convert the video audio.