For explainer videos and product demos, explainroo generates English narration and builds the video on your computer. Its open-source kit uses Kokoro, an open voice model, to read scripts in American or British English without an account or voice-generation API key.
explainroo creates an MP4 with narration, visuals, music, and timing - not just a voice file. It uses separate coding-agent software to create the video, and that provider may charge for its service.
How explainroo generates narration locally
With explainroo, Kokoro reads your script on your computer. The first setup downloads the voice and timing models; after that, explainroo handles video production locally. explainroo does not charge a per-video voice-generation fee, though the coding agent is a separate service and optional AI illustrations through OpenRouter cost money per image.
Local generation means explainroo creates the narration on your computer. This does not guarantee privacy for every part of your work. The coding agent is a separate service, and its terms govern how you use it. Narration is available in English, with American and British voices.
explainroo uses Whisper, a speech-recognition tool, to mark when each word is spoken and time the visuals to match. Chrome draws the scenes, and FFmpeg assembles them into an MP4. Setup requires recent Node.js and FFmpeg. It also requires Chrome or Chromium. You do not need a graphics card.
Compare explainroo and ElevenLabs
explainroo produces a narrated video. It does not provide a standalone voice file. Test its voice with your script to see whether it suits your narration. explainroo provides five visual styles and supports wide, tall, portrait, and square videos. Tall, portrait, and square versions include captions that light up one word at a time.
Cost and usage: explainroo itself is free and open source under the MIT license. Its video kit has no per-video charge, but the coding agent is a separate service with its own pricing, and optional AI illustrations are paid per image. Check ElevenLabs’ current plan, usage allowance, and terms before comparing costs; those details can change.
Voice and control: explainroo’s Kokoro voices cover natural American and British English. The pace setting in video.json adjusts voice speed, pauses, and animation speed. For a fair comparison with ElevenLabs, listen to the same script in both and check pronunciation, pacing, and whether the voice fits the video’s tone.
Setup and export: explainroo requires local setup or a coding agent that can run shell commands. The agent can install explainroo, create the video, check it, and provide an MP4. If your goal is an audio file to place into an existing editing workflow, confirm that the option you choose exports the format you need; explainroo’s documented output is a finished MP4.
Test both with one script
Choose a short script with the names, technical terms, and sentence lengths from your video. Give the same wording to each option. Listen for mispronunciations, uneven pauses, and a pace that makes the narration hard to follow. A voice that sounds good in a short sample also needs to work across the full script.
To create a sample video with explainroo, paste this prompt into a compatible coding agent, replacing 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 writes script.md with the spoken words and scenes.js with the drawings and scene timing. It then sets up explainroo, makes and checks the video, and gives you an MP4. Review the speech and visuals before using the video. explainroo provides still images of the scenes and a contact sheet. It also checks for overlapping or cut-off text and misheard words.
Choose the right fit
Choose explainroo for free, locally generated English narration in an explainer video or product demo. It supports coding agents that can run shell commands, including Claude Code, Codex, Pi, OpenCode, and Gemini CLI, and works best with Claude Code. For a product demo, tell the agent which product to show and where to find its code or website. explainroo can rebuild screens with the product’s colors, fonts, and button labels, then show a pointer clicking and typing as the narration explains.
Choose based on the finished audio and the work needed to make it. If you need more voice choices or control, compare the current options and terms directly with ElevenLabs using the same script. explainroo is designed for animated explainer videos and product demos. It does not 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.
What explainroo offers for video narration
- Try explainroo for a complete narrated video: Kokoro generates English narration locally, and explainroo combines it with visuals, timing, and sound in an MP4.
- Separate free software from other costs: explainroo has no per-video charge, but the coding agent is separately priced and optional AI illustrations cost money per image.
- Compare voices with identical wording: Listen for pronunciation, pacing, and fit before choosing explainroo or ElevenLabs.
- Check the format and workflow: explainroo outputs a finished MP4 and requires local tools or a compatible coding agent; it is not a drag-and-drop editor.
Conclusion
explainroo provides free local English narration for explainer videos and product demos. Test it with your script, account for the coding agent’s separate cost, and choose the option that provides the sound and output your project needs.
