skills.rest
takusaotome
takusaotomeCOMMUNITY
Explore all skills by this author →
GitHub

video2minutes

Generate meeting transcripts and structured Markdown minutes from video files.

5|4|Updated Nov 9, 2025
Search Tags:#summarization#markdown#video#transcription#ffmpeg#openai#meeting minutes
One-click install
npx skills add https://github.com/takusaotome/claude-skills-library --skill video2minutes
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video2minutes
Source: https://github.com/takusaotome/claude-skills-library/tree/main/skills/video2minutes
Command: npx skills add https://github.com/takusaotome/claude-skills-library --skill video2minutes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, python-dotenv, ffmpeg, ffmpeg-python, and includes scripts (resource) components.

What problem does it solve?

It converts meeting video files into readable transcripts and structured Markdown minutes, removing the time-consuming work of manually listening, typing, and organizing discussions.

Core Features & Use Cases

  • Video-to-transcript generation: Extracts audio from a video with FFmpeg and creates a text transcript via the OpenAI Whisper API.
  • Transcript-to-meeting-minutes writing: Uses an LLM to produce consulting-style minutes in Markdown with meeting info, an action-items table, and detailed discussion sections.
  • Meeting workflow use case: Use it for kickoff meetings or project syncs to generate minutes with attendees, decisions, topics, and next actions that can be shared right away.

Quick Start

Run the skill with your video path and required meeting metadata, for example: /video2minutes meeting.mp4 --date 2025-12-25 --attendees "田中, 佐藤" --meeting-name "キックオフ".

Frequently Asked Questions about video2minutes

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

FAQPage Schema
How do I automatically generate meeting minutes from a video file?▼

To generate meeting minutes from a video file, this Skill extracts audio using FFmpeg, transcribes it via the OpenAI Whisper API, and summarizes the text into structured Markdown using the OpenAI Chat Completions API.

Do I need an OpenAI API key to transcribe video to text?▼

Yes, you need an OpenAI API key to transcribe video to text, as the Skill relies on the OpenAI Whisper API for transcription and the Chat Completions API for summarization.

Can I use FFmpeg to extract audio for OpenAI transcription?▼

Yes, you can use FFmpeg to extract audio for OpenAI transcription; the Skill utilizes FFmpeg to isolate audio from the input video before sending it to the Whisper API.

What is the best way to convert a project sync video into Markdown meeting minutes?▼

The best way to convert a project sync video into Markdown minutes is passing the video path, date, attendees, and meeting name to this Skill, which outputs structured Markdown with action items and discussion topics.

What Python environment is required for video transcription and summarization?▼

Video transcription and summarization require Python 3.10 or higher, along with FFmpeg and the python-dotenv package installed to manage environment variables and audio extraction.

Why does my video to minutes workflow output separate transcript and Markdown files?▼

Your video to minutes workflow outputs separate files because the Skill saves the raw text transcript and the final summarized Markdown minutes into distinct, configurable directories for flexible documentation.

Related Skills

Explore More Content & Communication Skills→
aayushsoamaayushsoam
1

ascii-video

Convert video, audio, images, and text into ASCII character video using Python and ffmpeg.

Community
Advanced
githubgithub
37.6k

meeting-minutes

Generate standardized meeting minutes with decisions and action items.

Official
Basic
claude-office-skillsclaude-office-skills
368

Transcription Automation

Transcribe audio and video into text, meeting notes, and SRT subtitles.

Official
Advanced
ChatAndBuildChatAndBuild
1

transcribe

Transcribe audio files to text with optional speaker diarization via OpenAI API.

Official
Advanced