explainroo

Overview of explainroo

What it is

explainroo is a free and open-source tool that creates explainer videos and product demos. It uses a local voice model (Kokoro), word timing (Whisper), and a canvas renderer to turn a script into a narrated MP4 file. The voice, timing, and rendering all run on the user's computer.

Key features

• Voice: Kokoro reads the script aloud in English, Spanish, French, Italian, Brazilian Portuguese, Hindi, Japanese, or Mandarin Chinese. It has 54 voices and requires no account or API key. ElevenLabs voices or recorded narration can also be used.
• Timing: Whisper listens to the narration and notes when each word is spoken.
• Pictures: Chrome runs in the background and draws frames. Lines can look hand drawn (Rough.js). There are 1,800 icons from Lucide. Scenes can also show charts, math formulas, code that changes step by step, screenshots, and video clips.
• Camera: A camera films each scene. It moves in on what the voice talks about when there is time, and pulls back at the end. Cards and labels are never cut in half while a shot holds. Animations have a spring effect, and the final video includes motion blur.
• Sound: explainroo generates background music and small sound effects. The music becomes quieter while the voice speaks.
• File: ffmpeg produces an MP4 with subtitle files (.srt, .vtt), YouTube chapters, and a cover image.
• Looks: Six built-in looks are available: paper, clean, chalk, blueprint, midnight, and editorial. A project can also use a custom look defined in a JSON file.
• Sizes: Videos can be rendered in wide (YouTube), tall (Shorts, TikTok, Reels), 4:5 (Instagram, LinkedIn), and square. Tall, 4:5, and square videos get word-by-word captions.
• Product demos: The agent can rebuild an app's screens from its code or website, then a mouse pointer clicks through the screens and types into fields.
• Checks: explainroo provides stills, a layout check for cut-off or overlapping text, and a speech check for mispronounced words.

Use cases

• Creating short explainer videos for any topic.
• Producing product demos for software applications.
• Generating videos in multiple sizes for different social media platforms.
• Making videos with a consistent visual style using built-in or custom looks.

Getting started

bash git clone https://github.com/vincentsch/explainroo.git cd explainroo npm install node bin/explainroo.js doctor --fetch For narration in Spanish, French, Italian, Portuguese, or Hindi, also install espeak-ng (e.g., sudo apt install espeak-ng or brew install espeak-ng). Japanese and Chinese need Python with misaki, as described in AGENTS.md. After setup, start your coding agent in the explainroo folder and ask for a video.

License and pricing

explainroo is MIT licensed. It is free and open source.

Based on the project's public README and repository metadata.