baoyu-youtube-transcript

Extract YouTube transcripts, metadata, and cover images via InnerTube API.

3|Updated Jun 27, 2026
One-click install
npx skills add https://github.com/XinAloha/skills --skill baoyu-youtube-transcript-xinaloha
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-youtube-transcript
Source: https://github.com/XinAloha/skills/tree/main/productivity/youtube-transcript
Command: npx skills add https://github.com/XinAloha/skills --skill baoyu-youtube-transcript-xinaloha

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires bun, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the friction of manually transcribing or summarizing YouTube videos by providing an automated, high-fidelity extraction of subtitles, speaker identification, and chapter segmentation.

Core Features & Use Cases

  • Multi-Format Extraction: Download transcripts as clean Markdown or SRT files with precise timestamps.
  • Rich Metadata: Automatically fetches video descriptions, cover images, and chapter markers.
  • Speaker Identification: Uses AI post-processing to label speakers and structure dialogues for better readability.
  • Use Case: Quickly turn a long-form technical tutorial or interview into a structured, searchable document for your knowledge base.

Quick Start

Use the baoyu-youtube-transcript skill to download the transcript and chapters for the video at the provided URL.

Frequently Asked Questions about baoyu-youtube-transcript

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

FAQPage Schema
How do I extract YouTube transcripts and chapters from a video URL?

Extracting YouTube transcripts is handled automatically by fetching subtitles, chapter markers, and metadata via the InnerTube API, outputting clean Markdown or SRT files with precise timestamps and speaker identification.

Can I get multi-language subtitles from YouTube videos?

Multi-language subtitle retrieval is fully supported, allowing you to fetch available captions from YouTube videos and save them as structured SRT files or Markdown documents for content analysis.

Do I need bun or yt-dlp to download YouTube video transcripts?

Yes, the bun runtime is required to execute the transcript extraction scripts, while yt-dlp is an optional dependency used as a fallback for robust handling of restricted or blocked YouTube videos.

Does YouTube transcript extraction support speaker identification?

YouTube transcript extraction supports speaker identification by using AI post-processing to label different speakers and structure dialogues, improving readability for long-form technical tutorials and interviews.

What is the best way to convert a YouTube video into a searchable Markdown document?

Converting a YouTube video into a searchable Markdown document is best achieved by extracting transcripts, chapter markers, and speaker labels simultaneously, producing a structured knowledge base entry from long-form content.