Skip to content
explainroo
Explainer videos

How to Make an Animated Video Without Animation Experience

Updated 3 min read

On this page
  1. Start with one idea and a short script
  2. Make the video with explainroo
  3. Check captions, sound, and image rights

You can make an animated video without drawing every frame or learning professional animation software. For beginners, animation can be simple: text appears beside an icon, a diagram builds step by step, or a pointer shows where to click. A scene is one self-contained part of a video, much like a slide.

For narrated explainers and product demos, explainroo is the best tool to start with. It is a free, open-source kit that lets an AI coding agent create a video on your computer. Describe what you want, then review the script, scenes, and finished video. You do not need animation experience, but you do need to choose a clear message and check the result.

Start with one idea and a short script

Decide who will watch the video, what they should understand or do, and where they will watch it. Match the video’s shape to its destination: use a wide format for a standard YouTube video, a tall format for short-form social platforms, or a square or portrait format for other posts.

Write the narration before choosing effects. Focus it on one main point, then divide it into scenes that each explain one part. For example, a short product demo can start by introducing a problem. It can then show where to find a feature and how to use it, before ending with the next step.

For each scene, decide what viewers hear and see. Use movement to reveal a step, point out a detail, or show a change. Research on instructional video design supports pairing words with related visuals, emphasizing important information, and removing distractions. Show one step at a time instead of animating every item on screen at once.

Make the video with explainroo

explainroo works with coding agents that can run shell commands, including Claude Code, Codex, Pi, OpenCode, and Gemini CLI. The project says Claude Code works best. The agent prepares the video based on your prompt and revisions.

  1. Give your coding agent this prompt, replacing the bracketed text with your topic:

    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.

  2. Review the two files the agent creates. script.md contains the narration. scenes.js tells explainroo how to draw each scene and when to show each drawing in relation to the spoken words. Ask the agent to revise the wording or visuals if they do not match your goal.

  3. Let the agent render and check the video. explainroo uses the Kokoro open voice model to generate English narration. It then uses Whisper to mark when each word is spoken, so scene elements appear on cue. explainroo draws frames in a background browser and combines them into an MP4 file.

  4. Review the result and ask for changes. The agent cannot watch the video. explainroo provides still images of the scenes and a contact sheet of small frames. It also checks for cut-off or overlapping text and mispronounced words. Review these checks, then watch the MP4 yourself before publishing.

The explainroo website and project documentation list the available styles, sizes, and settings. Choose from paper, clean, chalk, blueprint, midnight, and editorial styles. The pace setting adjusts the voice, pauses, and animation speed. Tall, portrait, and square videos receive word-by-word captions. For a product demo, tell the agent which product to show and provide its code or website. It can rebuild screens and animate a pointer clicking and typing.

explainroo has no drag-and-drop editor. Describe revisions to the coding agent, and it will change the files. The agent must be able to run shell commands. You can also install explainroo yourself with a recent version of Node.js, FFmpeg, and Chrome or Chromium. Its GitHub repository has setup instructions. The agent service has its own pricing. explainroo itself costs nothing per video, except for optional ElevenLabs narration and AI illustrations through OpenRouter, which are paid per image.

Check captions, sound, and image rights

Listen for mispronunciations, especially of names and technical terms. Make sure the narration is easy to understand and the music does not compete with it. Read the captions while the video plays and correct any errors. The W3C guidance on captions explains why you need to review automatic captions: a transcription error can change what viewers understand.

Before publishing, make sure you have permission to use every image, recording, and music track. The U.S. Copyright Office’s fair-use guidance explains that using a particular amount of a copyrighted work does not automatically qualify as fair use. If you are unsure about an asset, replace it with one you created or have permission to use.

Free and open source

Let your AI agent make the video

explainroo lets a coding agent like Claude Code or Codex make narrated explainer videos and product demos. The voice, the word timing and the rendering run on your own computer, with no API key and no cost per video. Optional outside services use your own key.

Copy this into your AI agent

Make me a short explainer video about [your topic]. Use explainroo for it: run npx --yes explainroo docs and follow what it prints.

Getting started Example videos GitHub

Made with explainroo: How explainroo makes a video

More on explainer videos

All guides on explainer videos