youtube-transcribe-skill
Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles from a YouTube video.
When & Why to Use This Skill
This Claude skill automates the process of extracting subtitles and transcripts from YouTube videos. By leveraging both high-speed CLI tools (yt-dlp) and a robust browser automation fallback, it ensures reliable data retrieval even for videos with complex restrictions. It delivers organized, timestamped text files directly to your local environment, making it an essential tool for developers and researchers who need to bridge the gap between video content and text-based data processing.
Use Cases
- Content Repurposing: Quickly convert video scripts into blog posts, articles, or social media content to maximize reach across platforms.
- Research and Documentation: Extract dialogue from webinars, interviews, or educational lectures for easy reference, indexing, and qualitative analysis.
- Language Learning and Translation: Download transcripts in multiple languages to create study guides or as a baseline for professional translation workflows.
- Accessibility and SEO: Generate text versions of video content to improve accessibility for hearing-impaired users and enhance the searchability of video-based information.
| name | youtube-transcribe-skill |
|---|---|
| description | Extract subtitles/transcripts from a YouTube video URL and save as a local file. Use when you need to extract subtitles from a YouTube video. |
YouTube Transcript Extraction
Extract subtitles/transcripts from a YouTube video URL and save them as a local file.
Input YouTube URL: $ARGUMENTS
Step 1: Verify URL and Get Video Information
Verify URL Format: Confirm the input is a valid YouTube URL (supports
youtube.com/watch?v=oryoutu.be/formats).Get Video Information:
- If
yt-dlpis available, preferyt-dlp --get-title "[VIDEO_URL]". - If using browser automation, extract the title from the page (via snapshot or
document.title) for file naming.
- If
Step 2: CLI Quick Extraction (Priority Attempt)
Use command-line tools to quickly extract subtitles.
Check Tool Availability: Execute
which yt-dlp.- If
yt-dlpis found, proceed to subtitle download. - If
yt-dlpis NOT found, skip immediately to Step 3.
- If
Execute Subtitle Download (Only if
yt-dlpis found):- Tip: Always add
--cookies-from-browserto avoid sign-in restrictions. Default tochrome. - Retry Logic: If
yt-dlpfails with a browser error (e.g., "Could not open Chrome"), ask the user to specify their available browser (e.g.,firefox,safari,edge) and retry.
# Get the title first (try chrome first) yt-dlp --cookies-from-browser=chrome --get-title "[VIDEO_URL]" # Download subtitles yt-dlp --cookies-from-browser=chrome --write-auto-sub --write-sub --sub-lang zh-Hans,zh-Hant,en --skip-download --output "<Video Title>.%(ext)s" "[VIDEO_URL]"- Tip: Always add
Verify Results:
- Check the command exit code.
- Exit code 0 (Success): Subtitles have been saved locally, task complete.
- Exit code non-0 (Failure):
- If error is related to browser/cookies, ask user for correct browser and retry Step 2.
- If other errors (e.g., video unavailable), proceed to Step 3.
Step 3: Browser Automation (Fallback)
When the CLI method fails or yt-dlp is missing, use browser UI automation to extract subtitles.
Check Tool Availability:
- Check if
chrome-devtools-mcptools (specificallymcp__chrome__new_page) are available. - CRITICAL CHECK: If
chrome-devtools-mcpis NOT available ANDyt-dlpwas NOT found in Step 2:- STOP execution.
- Notify the User: "Unable to proceed. Please either install
yt-dlp(for fast CLI extraction) OR configurechrome-devtools-mcp(for browser automation)."
- Check if
Initialize Browser Session (If tools are available):
Call
mcp__chrome__new_pageto open the video URL.
3.2 Analyze Page State
Call mcp__chrome__take_snapshot to read the page accessibility tree.
3.3 Expand Video Description
Reason: The "Show transcript" button is usually hidden within the collapsed description area.
- Search the snapshot for a button labeled "...more", "...更多", or "Show more" (usually located in the description block below the video title).
- Call
mcp__chrome__clickto click that button.
3.4 Open Transcript Panel
- Call
mcp__chrome__take_snapshotto get the updated UI snapshot. - Search for a button labeled "Show transcript", "显示转录稿", or "内容转文字".
- Call
mcp__chrome__clickto click that button.
3.5 Extract Content via DOM
Reason: Directly reading the accessibility tree for long lists is slow and consumes many tokens; DOM injection is more efficient.
Call mcp__chrome__evaluate_script to execute the following JavaScript:
() => {
// Select all transcript segment containers
const segments = document.querySelectorAll("ytd-transcript-segment-renderer");
if (!segments.length) return "BUFFERING"; // Retry if empty
// Iterate and format as "timestamp text"
return Array.from(segments)
.map((seg) => {
const time = seg.querySelector(".segment-timestamp")?.innerText.trim();
const text = seg.querySelector(".segment-text")?.innerText.trim();
return `${time} ${text}`;
})
.join("\n");
};
If it returns "BUFFERING", wait a few seconds and retry.
3.6 Save and Cleanup
- Use the Write tool to save the extracted text as a local file (e.g.,
<Video Title>.txt). - Call
mcp__chrome__close_pageto release resources.
Output Requirements
- Save the subtitle file to the current working directory.
- Filename format:
<Video Title>.txt - File content format: Each line should be
Timestamp Subtitle Text. - Report upon completion: File path, subtitle language, total number of lines.