baoyu-youtube-transcript

Extract YouTube transcripts and cover images via InnerTube API or yt-dlp.

54|18|Updated Apr 2, 2026
One-click install
npx skills add https://github.com/open-fox/agents --skill baoyu-youtube-transcript-open-fox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-youtube-transcript
Source: https://github.com/open-fox/agents/tree/main/skills/baoyu-youtube-transcript
Command: npx skills add https://github.com/open-fox/agents --skill baoyu-youtube-transcript-open-fox

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables users to automatically fetch YouTube transcripts (subtitles) and the video cover image from a URL or video ID, reducing manual time spent gathering transcript data and visuals for content workflows.

Core Features & Use Cases

  • Downloads transcripts in multiple languages, including auto-generated captions, with optional translation support.
  • Generates a Markdown or SRT transcript with optional chapters and speaker-friendly formatting, and caches raw data for fast reformatting.
  • Fetches and caches cover images, metadata, and thumbnails for use in content pipelines or Obsidian notes.

Quick Start

Provide a YouTube URL or video ID to download the transcript and cover image, with optional language and translation settings.

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 automatically?

To download YouTube transcripts automatically, provide a video URL or ID to fetch subtitles in multiple languages, including auto-generated captions, formatted as Markdown or SRT.

Can I fetch auto-generated captions from YouTube videos?

Yes, you can fetch auto-generated captions from YouTube videos. The skill extracts auto-generated subtitles and supports optional translation for organizing multilingual transcript outputs.

How do I extract YouTube video cover images and metadata?

You extract YouTube video cover images and metadata by providing the video URL. The skill fetches and caches thumbnails and metadata for direct use in content pipelines or Obsidian notes.

Does the YouTube transcript fetcher support multiple languages and translation?

The YouTube transcript fetcher supports multiple languages and optional translation. It retrieves captions in various languages and can translate them to generate speaker-friendly formatted outputs.

What is the best way to get chapter-segmented YouTube transcripts?

The best way to get chapter-segmented YouTube transcripts is using a fetcher that structures outputs with optional chapters. This skill organizes transcript data into chapters and caches raw data for fast reformatting.

Why are my YouTube transcript fetches cached and how does reformatting work?

YouTube transcript fetches are cached to accelerate reformatting. The skill stores raw transcript data locally, allowing you to quickly regenerate outputs in Markdown or SRT without re-fetching from the API.