Summary
This extracts YouTube transcripts and saves them as Markdown files to your Obsidian vault at ~/Brains/brain/. It pulls subtitles via yt-dlp along with metadata like view counts, likes, and upload dates, then formats everything with YAML frontmatter. The transcript gets organized by video chapters if they exist, with timestamps for each segment. It's built for note-taking workflows where you want searchable text from videos without downloading the actual media. One nice touch is the deduplication script to clean up those annoying VTT subtitle artifacts where text accumulates line by line. English subtitles preferred, falls back to Russian.
Install to Claude Code
npx -y skills add glebis/claude-skills --skill youtube-transcript --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.mdView on GitHub
YouTube Transcript
Overview
Extract YouTube video transcripts, metadata, and chapters using yt-dlp. Output formatted as Markdown with YAML frontmatter, saved to ~/Brains/brain/ (Obsidian vault).
Quick Start
To extract a transcript from a YouTube video:
python scripts/extract_transcript.py <youtube_url>
Optional: Specify custom output filename:
python scripts/extract_transcript.py <youtube_url> custom_filename.md
Output Format
YAML Frontmatter
The generated Markdown includes comprehensive metadata:
title- Video titlechannel- Channel nameurl- YouTube URLupload_date- Upload date (YYYY-MM-DD)duration- Video duration (HH:MM:SS)description- Video description (truncated to 500 chars)tags- Array of video tagsview_count- View countlike_count- Like count
Body Structure
Transcript organized by video chapters (if available):
## Chapter Title
**00:05:23** Transcript text for this segment.
**00:05:45** Next segment text.
If no chapters exist, all content appears under "## Transcript" heading.
Timestamps formatted as HH:MM:SS for consistency.
Workflow
- Extract metadata and subtitles using yt-dlp
- Parse VTT subtitle format to extract timestamps and text
- Group transcript segments by video chapters (if present)
- Format as Markdown with YAML frontmatter
- Save to ~/Brains/brain/ with sanitized filename based on video title
- Clean up temporary subtitle files
Deduplication
To remove duplicates from existing transcript files:
python scripts/deduplicate_transcript.py <markdown_file>
This removes transcript entries that are prefixes of subsequent entries (common in VTT files where subtitles accumulate).
Requirements
Ensure yt-dlp is installed:
pip install yt-dlp
Limitations
- Extracts subtitles in English first, falls back to Russian if English unavailable
- Requires video to have subtitles (auto-generated or manual)
- Does not download video or audio files
- Description truncated to 500 characters in frontmatter
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
