If you need to explain a product, service, or unfamiliar idea in a short video, animation lets you show concepts that are hard to film. An animated explainer combines drawn or designed scenes with narration and sound to make the topic easier to understand. Many explainers run about 60 to 90 seconds, though the right length depends on what viewers need to understand.
If you want to make a narrated explainer on your computer, explainroo is the best fit if you are comfortable asking an AI coding agent to create and revise the video. This free, open-source kit turns a written request into an MP4. Describe the topic, review the video, and ask the agent to make changes.
Choose a format that fits the explanation
Use animation to show an abstract idea, sequence, or process. Choose live action when viewers need to see a physical product in use. Motion graphics animate text and visuals, such as charts, to explain information with numbers. Whiteboard videos draw while they explain, which helps break down complicated topics. Choose the format that best shows what viewers need to understand, as outlined in the four common explainer formats.
Animated explainers often appear on landing pages, product pages, onboarding sequences, and email campaigns. Use one to show viewers how something works. A promotional video aims to motivate a purchase or other action. If an explainer spends too much time selling, viewers who came to learn may stop watching.
Write the narration around the viewer’s problem
Start with the viewer’s problem, then explain how the product or idea solves it. A useful script has a hook, a body, and a call to action (CTA), which tells viewers what to do next. The AIDA framework offers one way to structure the script: get attention, build interest, create desire, and ask for action.
Do not open with a list of features. Viewers have little reason to care about product details until they understand the problem. Explain what difficulty the tool solves before describing its buttons or settings.
A 60-second English script is estimated at 140 to 150 words, but use that only as a starting point. Pauses, emphasis, pronunciation, and speaking pace affect the runtime. Read the script aloud and time it before building scenes. Explainer videos are commonly estimated to run one to two minutes, though some sources favor 60 to 90 seconds.
Match each scene to one idea
Plan visuals to match the narration. Show processes in sequence, use charts to explain quantities, and use screenshots when viewers need to recognize a product screen. Keep on-screen text brief so it supports the narration without competing with it.
A simple storyboard pairs each narration line with a visual idea. In a product demo, for example, show a pointer clicking a button as the narration explains it. Bring in each visual when the narration reaches that point instead of showing everything at once.
Make the video with explainroo
explainroo works with coding agents that run shell commands, including Claude Code, Codex, Pi, OpenCode, and Gemini CLI. Claude Code works best with explainroo. To begin, paste this prompt into your agent and replace the bracketed 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.
The agent sets up explainroo, creates and checks the video, then gives you an MP4. It creates script.md for the narration and scenes.js for the drawings and scene timing. Ask the agent to revise either file if the wording or visuals need work.
The kit uses Kokoro, an open voice model with American and British English voices. No account or API key is required for Kokoro, and narration is in English and seven other languages. Whisper, a speech-recognition tool, marks when each word is spoken so visuals can appear at the right time. Chrome draws frames on an HTML canvas. FFmpeg combines the frames, narration, and sound into an MP4.
To request a product demo, name the product and provide its code or website. explainroo rebuilds the screens with the product’s colors, fonts, and button labels. It then shows a pointer clicking and typing as the narration explains the product.
In video.json, choose a visual look: paper, clean, chalk, blueprint, midnight, or editorial. The file also controls the pace and format. Choose wide for YouTube, tall for YouTube Shorts, TikTok, or Instagram Reels, portrait for Instagram or LinkedIn posts, or square. Tall, portrait, and square videos include captions that light up word by word. Tall videos also keep text clear of the areas where social platforms place buttons.
The kit creates background music for each video and adds sound effects. It lowers the music during narration. You can also add AI illustrations through OpenRouter, which charges per image. The other video-making features are free per video with built-in voices. The coding agent is a separate service and may charge its own fee.
Check the video before sharing it
Listen for mispronounced names and technical terms. Watch for scenes that appear too early or late, hard-to-read text, and visuals that do not clarify the narration.
An AI coding agent cannot watch a video. explainroo helps the agent review it with still images of scenes and a contact sheet of small frames. It also checks for cut-off or overlapping text and uses a speech check to catch mispronounced words. Run those checks, then watch the MP4 yourself before publishing.
To install the kit yourself, you need recent Node.js, FFmpeg, and Chrome or Chromium. The first setup downloads the voice and timing models. explainroo is developed on Linux, and its tests run on Linux, macOS, and Windows. Find installation instructions and examples in the explainroo documentation and video gallery.
explainroo creates animated explainers and product demos. It cannot edit existing camera footage or create talking avatars or live-action AI footage. It also has no drag-and-drop editor. Describe the video to the agent and ask for changes. The open-source project is available under the MIT license.