baoyu-youtube-transcript

Retrieves YouTube transcripts and cover images from URLs or IDs via InnerTube or yt-dlp with caching.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/cvenwu/AiFlow --skill baoyu-youtube-transcript-cvenwu
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-youtube-transcript
Source: https://github.com/cvenwu/AiFlow/tree/main/skills/baoyu-youtube-transcript
Command: npx skills add https://github.com/cvenwu/AiFlow --skill baoyu-youtube-transcript-cvenwu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill automates the retrieval of YouTube transcripts and cover images, saving time and reducing manual copy-paste when archiving video content.

Core Features & Use Cases

  • Transcript retrieval from YouTube through InnerTube API or yt-dlp fallback.
  • Multi-language support and translation when available.
  • Chapters and speaker identification to structure transcripts, with caching for fast re-formatting.

Quick Start

Provide a YouTube URL or video ID to download transcripts, metadata, chapters, and a cover image.

Frequently Asked Questions about baoyu-youtube-transcript

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

FAQPage Schema
How do I automatically download YouTube transcripts and video covers from a URL?▼

To download YouTube transcripts and video covers automatically, provide a video URL or ID to retrieve multi-language captions, chapters, speaker labels, and cover images via InnerTube API.

Can I extract YouTube transcripts in multiple languages with speaker identification?▼

Yes, YouTube transcript extraction supports multi-language captions with translation when available, alongside chapter parsing and speaker labeling to structure the retrieved text.

Does YouTube transcript retrieval work with yt-dlp as a fallback?▼

YouTube transcript retrieval uses yt-dlp as a fallback when the primary InnerTube API fails, ensuring consistent access to captions and metadata across different video configurations.

How does caching optimize repeated YouTube transcript formatting?▼

Caching stores previously retrieved YouTube transcripts and metadata to optimize repeat access, enabling fast re-formatting of chapters and speaker labels without re-fetching data from the source.

Do I need a bun runtime environment to fetch YouTube video transcripts?▼

Yes, the bun runtime is required to execute the automated YouTube transcript and cover image retrieval scripts that interface with the InnerTube API and yt-dlp fallback.

What YouTube metadata is included when extracting video transcripts?▼

Extracting YouTube transcripts includes multi-language captions, chapter parsing, speaker identification, video metadata, and cover images, all retrieved end-to-end from a single video URL or ID.