explainroo

What it does

You ask your coding agent for a video, for example:

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 writes two files. script.md has the words the voice says. scenes.js draws the pictures with JavaScript. Each drawing can appear on a word the voice says.

How it works

• Voice. Kokoro, an open voice model, reads the script aloud. It has 28 voices and needs no account or API key.
• Timing. Whisper listens to the recording and notes when each word is spoken.
• Pictures. Chrome runs in the background and draws the frames.
• Sound. Music and small sound effects. The music gets quieter while the voice speaks.
• File. ffmpeg puts it all together into an MP4.

None of this leaves your computer, and it costs nothing. Your coding agent is a separate service with its own terms and prices.

Looks and sizes

Five looks: paper, clean, chalk, blueprint and midnight. Sizes for YouTube, Shorts, TikTok, Reels, Instagram, LinkedIn and a square one. Tall, 4:5 and square videos get captions that light up word by word.

Product demos

explainroo can also make product demos. The agent rebuilds the app's screens from its code or website, and a mouse pointer clicks through them.

Setup

You need Node.js 20.11 or newer, ffmpeg, and Chrome or Chromium. The first setup downloads the voice and timing models once, about 400 MB together.

Examples: https://www.explainroo.com/

Code: https://github.com/vincentsch/explainroo (MIT license)