youtube-transcript

Download YouTube transcripts and convert VTT subtitles into deduplicated plain text.

Updated May 26, 2026
One-click install
npx skills add https://github.com/XWIlluDelu/agent-share --skill youtube-transcript-xwilludelu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/XWIlluDelu/agent-share/tree/main/lib/youtube-transcript
Command: npx skills add https://github.com/XWIlluDelu/agent-share --skill youtube-transcript-xwilludelu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of manually searching for, downloading, or transcribing YouTube captions when you need the transcript as usable text.

Core Features & Use Cases

  • Subtitle discovery and selection: Checks which manual or auto-generated subtitle tracks are available before downloading.
  • Transcript download with quality fallback: Downloads manual subtitles first, falls back to auto-captions, and uses Whisper transcription only when captions are unavailable.
  • Readable plain-text output: Converts VTT subtitles into deduplicated plain text suitable for reading, summarization, or downstream analysis, while also supporting keeping the VTT format when needed.

Quick Start

Ask the assistant to download the transcript from your YouTube URL and return it as plain text.

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 captions as plain text?▼

To download YouTube captions as plain text, provide the video URL to trigger subtitle discovery and download. The tool retrieves manual subtitles first, falls back to auto-captions, and post-processes VTT files into deduplicated readable text.

What happens when a YouTube video has no manual subtitles?▼

When manual subtitles are missing, the tool falls back to downloading auto-generated captions. If auto-captions are also unavailable, it optionally runs Whisper transcription after user confirmation to generate the video transcript.

Do I need yt-dlp to extract YouTube transcripts?▼

Yes, yt-dlp is required to list available subtitle tracks and perform manual then auto-caption retrieval from YouTube. It serves as the core engine for discovering and downloading VTT subtitle files for text conversion.

Can I keep the original VTT subtitle format instead of plain text?▼

Yes, you can keep the VTT subtitle format instead of converting to plain text. While the default output is deduplicated readable text, the tool supports retaining the original VTT format when needed for downstream use.

How does Whisper transcription work for missing YouTube captions?▼

Whisper transcription runs only when both manual and auto-captions are unavailable. It requires user confirmation for large downloads, then transcribes the video audio to produce a readable text transcript.