# AI use cases for Explainroo (vincentsch/explainroo) Repo: [vincentsch/explainroo](https://github.com/vincentsch/explainroo) | Use cases: 4 | Page: https://dedupedai.com/use-cases/vincentsch-explainroo/ explainroo is a free, open source tool that turns a script and JavaScript scene file into a narrated explainer video or product demo MP4, with the voice, timing and rendering running on your computer. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Make a narrated explainer video from one topic: https://dedupedai.com/use-cases/vincentsch-explainroo/make-explainer-video-from-topic/ - Build a product demo that clicks through your app: https://dedupedai.com/use-cases/vincentsch-explainroo/build-product-demo-for-your-app/ - Render one video in wide and tall sizes at once: https://dedupedai.com/use-cases/vincentsch-explainroo/render-one-video-for-every-feed/ - Narrate an explainer in another language: https://dedupedai.com/use-cases/vincentsch-explainroo/narrate-explainer-in-another-language/ ## How to make a narrated explainer video from one topic with Explainroo Repo: [vincentsch/explainroo](https://github.com/vincentsch/explainroo) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Give a coding agent a topic and get a narrated MP4 with drawn scenes and subtitles. **Who it is for:** A teacher, founder or content creator who needs a short explainer on one topic and does not want to edit video by hand. **The problem:** Making an explainer video usually means writing a script, recording a voice, drawing scenes and syncing them by hand. **The outcome:** An MP4 where a local voice narrates the script and drawings appear on the words they match, plus subtitle files and a cover image. ### Steps 1. Clone the repo with `git clone https://github.com/vincentsch/explainroo.git` 2. Enter the folder with `cd explainroo` and install dependencies with `npm install` 3. Download the voice and timing models with `node bin/explainroo.js doctor --fetch` 4. Start your coding agent in the Explainroo folder and give it the topic prompt below 5. Open the MP4 the agent saves under videos/ and watch it to confirm the narration matches the drawings ### Prompt to paste into your agent ```text Use the explainroo repo at to make a short explainer video about . Read AGENTS.md and follow its steps so the agent writes script.md and scenes.js and renders an MP4. Expected output: one MP4 under videos/. Verify that the voice reads the script without wrong words before you report the file path. ``` ### Caveat The README says the agent works best with Claude Code and Opus 5.5, so results with other agents may vary. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/vincentsch-explainroo/make-explainer-video-from-topic/ ## How to build a product demo that clicks through your app with Explainroo Repo: [vincentsch/explainroo](https://github.com/vincentsch/explainroo) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Rebuild your app's screens in Explainroo and film a pointer walking through them. **Who it is for:** A founder or product marketer who needs a demo video for a web app before a launch or sales call. **The problem:** Screen recordings of a real app are hard to re-cut, and changing a button label means filming again. **The outcome:** A product demo MP4 with screens built from your code or site, your colors and fonts, and a mouse pointer that clicks through the flow. ### Steps 1. Complete the install steps with `git clone https://github.com/vincentsch/explainroo.git`, `cd explainroo`, `npm install` and `node bin/explainroo.js doctor --fetch` 2. Run `explainroo capture` against your own live site to save its screenshots, colors, fonts, logo and wording (inferred, check the README) 3. Tell your agent which product it is and where its code or website lives, then have it rebuild the screens in scenes.js 4. Render the demo with `explainroo render videos/` and check the stills for cut-off or overlapping text (inferred, check the README) 5. Read the layout check output and fix any flagged scenes before you publish ### Prompt to paste into your agent ```text In the explainroo repo at , make a product demo for using its site at . Rebuild its screens with the same colors, fonts and button labels, then render an MP4. Expected output: one product demo MP4. Verify that every button label matches the real product before you publish. ``` ### Caveat The README shows demos for the author's own products and unofficial demos of Gmail, ChatGPT and Claude, and it does not describe any approval process for demos of third-party products. Risk, reverse engineering: Capturing a live site's screenshots, colors, fonts, logo and wording and rebuilding its screens can copy someone else's product look, so get permission before you publish a demo of a product you do not own. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/vincentsch-explainroo/build-product-demo-for-your-app/ ## How to render one video in wide and tall sizes at once with Explainroo Repo: [vincentsch/explainroo](https://github.com/vincentsch/explainroo) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Make one project into a YouTube video and a TikTok or Reels version in one step. **Who it is for:** A creator who posts the same explainer to YouTube, Shorts, TikTok and Instagram and wants each size without re-editing. **The problem:** Each platform needs a different frame size, and reformatting a finished video by hand loses captions and timing. **The outcome:** Separate renders of one project in wide, tall and square sizes, each with word-by-word captions where the size supports them. ### Steps 1. Set up Explainroo with `npm install` and `node bin/explainroo.js doctor --fetch` inside the repo folder 2. Render the wide version and the tall version with `explainroo render videos/demo --size tiktok` 3. Add `"watermark": false` to video.json only if you have a reason to remove the corner watermark 4. Check small text for a phone screen with `explainroo check videos/ --view-width 854` 5. Upload the MP4 with the .srt or .vtt subtitle file and the chapters the render writes ### Prompt to paste into your agent ```text In the explainroo repo at , render the project at videos/ in the wide size and the tiktok size. Expected output: two MP4 files next to each other. Verify that the tall version keeps your text clear of the platform buttons before you upload. ``` ### Caveat The README says the watermark helps other people find Explainroo, and removing it with "watermark": false is up to you. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/vincentsch-explainroo/render-one-video-for-every-feed/ ## How to narrate an explainer in another language with Explainroo Repo: [vincentsch/explainroo](https://github.com/vincentsch/explainroo) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Render the same script with a local voice in Spanish, Japanese or another supported language. **Who it is for:** A teacher or creator who wants the same explainer for viewers who speak Spanish, French, Japanese or Chinese. **The problem:** Re-recording a narration in each language costs time and money, and a machine voice that mispronounces words is hard to spot. **The outcome:** An MP4 narrated in the chosen language by a local voice, with a speech check that flags words the voice got wrong. ### Steps 1. Install espeak-ng for Spanish, French, Italian, Portuguese or Hindi, for example with `sudo apt install espeak-ng` or `brew install espeak-ng` 2. For Japanese or Chinese, install Python with misaki as described in AGENTS.md under the Japanese and Chinese section 3. Write script.md in the language you want the voice to speak 4. Render the video with `explainroo render videos/` (inferred, check the README) 5. Read the speech check output and fix any words the voice got wrong before you publish ### Prompt to paste into your agent ```text In the explainroo repo at , write a script in and render an explainer video for . Expected output: one MP4 narrated in that language. Verify that the speech check reports no wrong words before you report the file path. ``` ### Caveat The README says the non-English voices need espeak-ng or Python with misaki, so the setup takes longer than the English path. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/vincentsch-explainroo/narrate-explainer-in-another-language/