youtube-transcript

Extract YouTube video transcripts via subtitles or Whisper audio transcription.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/UNO998/rla_skills --skill youtube-transcript-uno998
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/UNO998/rla_skills/tree/main/youtube-transcript
Command: npx skills add https://github.com/UNO998/rla_skills --skill youtube-transcript-uno998

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Download transcripts for YouTube videos by extracting subtitles or transcribing audio when captions are unavailable.

Core Features & Use Cases

  • Subtitle download: Retrieve manual or auto subtitles for a YouTube URL.
  • Whisper fallback: Transcribe audio when subtitles don't exist.
  • Post-processing: Convert to plain text for easy analysis.

Quick Start

Provide a YouTube URL and I will fetch or generate its transcript.

Frequently Asked Questions about youtube-transcript

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

FAQPage Schema
How do I extract subtitles from a YouTube video?

To extract YouTube subtitles, provide the video URL and the tool fetches available captions, prioritizing manual subtitles over auto-generated ones before converting them into plain text.

Can I transcribe YouTube audio when subtitles are unavailable?

Yes, you can transcribe YouTube audio using Whisper as a fallback when no manual or auto-generated subtitles exist, requiring optional Whisper setup and user confirmation for large audio downloads.

Do I need yt-dlp installed to download YouTube transcripts?

Yes, yt-dlp is a required dependency for downloading YouTube transcripts, and the tool will guide you through the installation process to ensure subtitle extraction functions correctly.

What is the best way to get plain text from YouTube auto-generated captions?

The best way to get plain text from YouTube auto-captions is to fetch the auto-generated subtitles via yt-dlp and apply post-processing to convert the extracted results into clean plain text.

How does Whisper transcription compare to downloading native YouTube subtitles?

Downloading native YouTube subtitles is faster and prioritized, while Whisper transcription serves as a slower fallback to transcribe audio directly when no caption tracks are available.

Are there limitations when fetching transcripts for long YouTube videos?

For long YouTube videos, limitations include requiring user confirmation for large audio downloads when using Whisper, though native subtitle extraction via yt-dlp remains efficient regardless of length.