baoyu-youtube-transcript

Download YouTube transcripts and cover images by URL or video ID.

Updated Feb 6, 2026
One-click install
npx skills add https://github.com/glfruit/gorin-skills --skill baoyu-youtube-transcript-glfruit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-youtube-transcript
Source: https://github.com/glfruit/gorin-skills/tree/main/openclaw/baoyu-youtube-transcript
Command: npx skills add https://github.com/glfruit/gorin-skills --skill baoyu-youtube-transcript-glfruit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Downloads YouTube video transcripts and cover images by URL or video ID for downstream AI workflows.

Core Features & Use Cases

  • Multi-language transcript retrieval with optional translation
  • Chapter segmentation and speaker identification
  • Caching of transcripts, metadata, and cover images to speed up re-formatting

Quick Start

Fetch transcripts and a cover image for a YouTube video by URL or ID.

Frequently Asked Questions about baoyu-youtube-transcript

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

FAQPage Schema
How do I download YouTube transcripts and subtitles for multiple languages?

You can download YouTube transcripts in multiple languages by providing the video URL or ID and specifying the target language. The tool fetches subtitles via InnerTube or yt-dlp and supports optional translation to retrieve the desired transcript text.

What is the best way to extract YouTube video chapters and speaker identification from subtitles?

Extracting YouTube video chapters and speaker identification requires parsing subtitle metadata during the transcript download. This skill segments transcripts by chapter and labels speakers, producing structured text output for downstream analysis.

Can I fetch YouTube thumbnails and cover images using yt-dlp?

Yes, you can fetch YouTube thumbnails and cover images using yt-dlp. This skill leverages yt-dlp alongside InnerTube to retrieve video metadata and downloads cover images directly by URL or video ID for immediate use.

Does fetching YouTube transcripts with InnerTube cache metadata and subtitles?

Yes, fetching YouTube transcripts with InnerTube caches metadata, subtitles, and cover images. This caching mechanism speeds up re-formatting and subsequent retrieval processes by storing previously fetched artifacts locally for faster access.

How do I get YouTube transcripts ready for AI workflows?

To get YouTube transcripts ready for AI workflows, download the subtitles with chapter segmentation and speaker identification enabled. This skill exposes ready-to-use text artifacts with cached metadata, making the output directly consumable by downstream AI tools.

Why do I need a YouTube video ID to retrieve subtitles and cover images?

You need a YouTube video ID or URL to retrieve subtitles and cover images because it serves as the unique identifier for fetching metadata via InnerTube or yt-dlp. Without it, the tool cannot locate the specific video transcript or thumbnail assets.