video-to-markdown

Extract speech from online videos into timestamped Markdown transcripts with summaries.

2|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/imbatony/copilot-tools --skill video-to-markdown
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-to-markdown
Source: https://github.com/imbatony/copilot-tools/tree/main/.github/skills/video-to-markdown
Command: npx skills add https://github.com/imbatony/copilot-tools --skill video-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, ffmpeg, whisper, openai-whisper, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill converts video content into a structured, timestamped Markdown transcript with a separate key-points summary, removing the manual burden of manual transcription and note-taking.

Core Features & Use Cases

  • Automatic Transcripts: Extract speech from online videos and produce a complete, timestamped transcript.
  • Structured Markdown Output: Generate a Markdown document with a full subtitle section and a concise summary of key points.
  • Versatile Use: Video notes, research extraction, teaching materials, and content repurposing for reports.

Quick Start

Provide a video URL and let the tool generate a Markdown document with complete subtitles and a concise summary.

Frequently Asked Questions about video-to-markdown

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

FAQPage Schema
How do I convert video to markdown notes with timestamps?

To convert video to markdown notes, this tool extracts speech and outputs a structured, timestamped markdown transcript alongside a concise key-points summary for reading.

Can I extract subtitles from YouTube or Bilibili videos automatically?

Yes, you can extract subtitles from YouTube or Bilibili automatically. The workflow uses yt-dlp and ffmpeg for media handling to fetch existing subtitles directly from the video.

Does video transcription work if the online video has no embedded subtitles?

Video transcription still works without embedded subtitles by applying optional Whisper transcription. This uses openai-whisper to automatically transcribe the extracted audio speech into text.

What is the best way to generate a key-points summary from video content?

The best way to generate a key-points summary from video content is using an automated workflow that transcribes the audio and outputs a separate markdown summary section alongside the full transcript.

Do I need ffmpeg and yt-dlp installed to extract speech from online videos?

Yes, you need ffmpeg and yt-dlp installed. This workflow implements an end-to-end process using these dependencies for media handling and audio extraction before transcription can occur.