A narrated presentation video is a fixed sequence of visuals and spoken explanation that plays on its own. Viewers cannot interrupt the video to ask for clarification, so the narration must explain the slides’ main points. Keep each scene on screen long enough for viewers to follow along.
For a narrated explainer based on your presentation, explainroo is the best fit: it uses a coding agent to create a video with narration and drawn scenes. You describe the topic and content for the agent, which produces an MP4. explainroo builds a new video, so plan to reuse the deck’s ideas and important visuals. It does not work as a drag-and-drop slide editor.
Shape the slides into a story
Start by deciding what viewers should understand or do after watching. Then arrange the material into a clear sequence: introduce the topic, explain each main point, and close with a conclusion or next step.
In a live presentation, the speaker can fill in missing context. In a video, the narration must provide it. For each chart, diagram, or image, say what viewers should notice. For example, replace “Here’s our sales chart” with “Revenue rose from the first quarter to the fourth, with the steepest increase after the product launch.”
In one study of 90 presentation videos, 72% of the 610 visual elements examined were not described clearly enough in the speech. The finding applies to the videos in that study, but it points to a common production risk: viewers may not know which visual detail matters unless the narrator says so. The study offers feedback aimed at improving access to presentations for people who cannot rely on the visuals.
Keep slides focused on a few labels, figures, or images rather than putting the full narration on screen. Divide long presentations at meaningful topic changes. Research supports splitting multimedia lessons into segments, but does not identify one ideal video length for every subject. A systematic review reports that results depend on factors such as the topic and the learner’s prior knowledge.
Make the video with explainroo
explainroo is a free, open-source kit under the MIT license. It works with coding agents that can run shell commands, and its documentation says it works best with Claude Code. The agent writes script.md, which contains the narration, and scenes.js, which describes the visuals. explainroo then builds and checks the video on your computer.
To get started, give your agent this prompt, replacing the bracketed text with your subject:
Make me a short explainer video about [your topic]. Use explainroo for it: clone the explainroo repository, read its AGENTS.md and follow the steps.
For a video based on a presentation, give the agent the deck’s main points and intended audience. Describe any charts or visuals the narration must explain. The agent uses those details to build scenes. It can also use screenshots, charts, code, and icons. If you want a product demo, tell the agent which product to show and where its code or website is.
explainroo’s Kokoro voice reads the script aloud in English. You can choose from American and British English voices. Whisper, a speech-recognition model, marks when each word is spoken so visuals can appear on cue. Chrome draws the frames, and FFmpeg combines them into an MP4. The agent checks scene images and a contact sheet for overlapping or cut-off text, and checks for possible mispronunciations. It cannot watch the video, so you still need to review the finished file yourself. See example videos and the explainroo documentation for more.
Review the video and make it accessible
Watch the full MP4 before sharing it. Check that the narration is clear, scenes stay on screen long enough, and charts or text are readable at the size viewers will see them. Confirm that the visuals appear when the narration discusses them, and correct any pronunciation or caption errors.
Add captions to display spoken words in sync with the audio. Automatic captions need review: W3C guidance warns that errors can change the meaning. A transcript gives viewers a text version to read, search, or use with assistive technology. When the video contains meaningful visual information, include that information in the narration or transcript as well.
Tall, portrait, and square explainroo videos receive captions that light up word by word. The kit also offers wide format for YouTube and tall format for short-form social video. Its narration is English only. There is no per-video charge for explainroo. Optional AI illustrations through OpenRouter cost per image, and the coding agent is a separate service with its own pricing.
