thevibemarketershq

thevibemarketershq / video-to-guide

Public

Turn any screen recording into a polished HTML guide in ~10 min. Works in Claude Code + Hermes. Mac, Linux, Windows.

17
2
89% credibility
Found May 29, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Shell
AI Summary

A tool that converts screen recordings into polished, step-by-step HTML tutorials by automatically finding key moments, extracting screenshots, and generating a complete guide file.

How It Works

1
🎥 You record your screen

You record your screen while showing someone how to do something on your computer.

2
💭 You want to create a tutorial

You want to turn that video into a clear, step-by-step guide you can share with anyone.

3
✨ You run the video-to-guide skill

You ask your AI assistant to turn your video into a guide, and it checks that everything is ready to go.

4
🎯 Your video gets analyzed automatically

The tool listens to your video, finds the important moments, and takes screenshots at exactly the right times.

5
📝 Your guide is written for you

The AI writes out clear steps, adds helpful tips, and builds a complete HTML file with all your screenshots included.

🎉 Your guide is ready to share

You get a beautiful, polished guide that works in any browser — no special software needed.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 17 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is video-to-guide?

This is a CLI tool that converts screen recordings into polished HTML guides. Drop in an MP4 or MOV file, and it produces a complete step-by-step guide with screenshots, timestamps, and clean formatting. The workflow uses Whisper for transcription, ffmpeg for frame extraction, and Python for processing. The key differentiator is transcript-guided extraction: instead of grabbing frames at random intervals, it analyzes the audio transcript to identify action moments, giving you 6-12 useful screenshots instead of 88 useless ones. Output is a single self-contained HTML file with base64-encoded images.

Why is it gaining traction?

The transcript-guided approach solves the core pain of screen recording documentation. Most tools flood you with screenshots; this one curates them. It integrates directly with Claude Code and Hermes, fitting into AI-native development workflows. The self-contained HTML output (no external hosting required) is a practical touch for sharing guides via email or USB. Fallback methods handle different ffmpeg versions and edge cases automatically.

Who should use this?

Devs creating internal documentation from screen recordings. Content teams building tutorials without screenshotting manually. Support teams turning recorded walkthroughs into searchable guides. Anyone who records their screen and wants the output to actually be useful.

Verdict

With 17 stars and a credibility score of 0.8999999761581421%, this is early-stage software from an unknown source. The documentation is thorough and the core idea is solid, but there's no test suite visible and it's a one-person operation. Worth evaluating for your workflow if you need this capability, but don't stake critical documentation processes on it yet.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.