What file format is the final output?

The skill processes raw subtitle files and saves them as clean .txt files, removing technical metadata for better readability.

Does it support auto-generated captions?

Yes, the skill is configured to fall back to auto-generated subtitles if manually uploaded tracks are not available.

Can I download subtitles for private or member-only videos?

Yes, the skill can utilize cookies from your local browser (Chrome, Firefox, Edge, etc.) to authenticate and download subtitles for restricted content you have access to.

Which video platforms does this skill support?

It supports all platforms compatible with the yt-dlp engine, including major sites like YouTube, Bilibili, Twitter/X, Vimeo, and TikTok.

Video Subtitle Extractor

Name: Video Subtitle Extractor
Author: wuyuxiangX

bywuyuxiangX

웹 스크래핑 및 데이터 수집

Extracts and cleans transcripts from global video platforms like YouTube and Bilibili into readable text files.

소개

The Video Subtitle Extractor is a specialized Claude Code skill designed to automate the retrieval of spoken content from video URLs. By leveraging yt-dlp, it can access official subtitles, auto-generated captions, and transcripts from platforms including YouTube, Bilibili, Twitter/X, and TikTok. The skill goes beyond simple downloading by automatically stripping timestamps and formatting tags to produce a clean, plain-text transcript, making it an essential tool for researchers, content creators, and developers building video-to-text workflows.

주요 기능

Standardized output format optimized for downstream AI processing
Smart language detection for Chinese, English, Japanese, and Korean
Supports 1000+ video platforms via yt-dlp integration
Automatic cleaning of VTT/SRT formatting and timestamps
0 GitHub stars
Browser cookie integration for accessing member-only or age-restricted content

사용 사례

Converting video tutorials into searchable documentation or blog posts
Generating clean text datasets from video repositories for LLM training
Extracting dialogue from webinars for research and sentiment analysis

소개

주요 기능

Standardized output format optimized for downstream AI processing
Smart language detection for Chinese, English, Japanese, and Korean
Supports 1000+ video platforms via yt-dlp integration
Automatic cleaning of VTT/SRT formatting and timestamps
0 GitHub stars
Browser cookie integration for accessing member-only or age-restricted content

사용 사례

Converting video tutorials into searchable documentation or blog posts
Generating clean text datasets from video repositories for LLM training
Extracting dialogue from webinars for research and sentiment analysis