Skip to content
explainroo

Docs

Getting started

What you need, how to install explainroo, and how to get your first video.

What do I need?

  • A coding agent. explainroo works with Claude Code, Codex, Pi and other agents that can run commands and read files. Right now it works best with Claude Code and Opus 5.5.
  • Node.js 20.11 or newer.
  • ffmpeg.
  • Google Chrome or Chromium. If you have neither, run npx playwright install chromium-headless-shell. It installs a small version of Chromium that explainroo can use.
  • About 400 MB of free disk space for the speech models.

You don’t need an API key or a graphics card. You only need an OpenRouter key if you want AI images. I develop and test explainroo on Linux. It should work on macOS and Windows too, but I have tested it less there so far.

How do I install it?

git clone https://github.com/vincentsch/explainroo.git
cd explainroo
npm install
node bin/explainroo.js doctor --fetch

doctor checks that Node, ffmpeg and Chrome are there. It also downloads the voice model and the speech check model from Hugging Face. They go into ~/.cache/explainroo/models, and that download happens only once.

If you run npm link in the folder, you can type explainroo instead of node bin/explainroo.js.

How do I get my first video?

The quickest way is to copy this prompt into your agent. Put your topic in place of the brackets:

Make me a short explainer video about [your topic]. Use explainroo for it: clone https://github.com/vincentsch/explainroo, read its AGENTS.md and follow the steps.

The agent clones explainroo, installs it and makes the video. If you have already installed explainroo yourself, start your agent in the explainroo folder and tell it what you want. For example:

Make a 60 second video about how HTTPS keeps a password secret.

Either way, the agent reads AGENTS.md in the repo, which tells it how to make a video. It creates a project in videos/, writes the script, makes the voice, draws the scenes and checks its work. Then it saves the video. The finished file is videos/<name>/out/video.mp4.

You can tell the agent more, like a length, a look or a voice. You can ask for a tall video for Shorts, give it your own screenshots, or point it to a page or folder to read. The agent asks you when it can’t go on without an answer. That happens when you want AI images and it has no OpenRouter key, for example.

Can I make a video without an agent?

Yes. The agent only writes files and runs commands, and you can do the same:

node bin/explainroo.js init videos/hello --theme paper --title "Hello"
node bin/explainroo.js preview videos/hello
node bin/explainroo.js render videos/hello

init creates a small starter project with three scenes. preview shows the video in your browser while you work on it. It reloads when you save script.md or scenes.js. render makes the video file and writes it to videos/hello/out/video.mp4.

The next pages explain how explainroo works, how to write the script and how to draw the scenes.