Yes. Google Gemini can generate short videos from text prompts, uploaded images, or videos. You can then ask for changes in a conversation. To generate videos, you need a Google AI plan or a qualifying Workspace license. Users under 18 cannot use the feature. Videos made in Gemini Apps carry a SynthID watermark, an invisible mark that identifies AI-generated content. See Google’s Gemini video help for current account details.
For a narrated explainer or product demo with scenes timed to a script, explainroo is a better fit. An AI coding agent creates and assembles the video on your computer. Gemini’s chat interface generates short clips.
What Gemini video generation does
You can give Gemini a text description, photo, or video. Describe the scene or motion you want, review the result, and ask for changes in plain language. Google explains this approach on its Gemini video-generation page.
Gemini is useful for making a short visual moment, animating an image, or exploring a scene idea. It does not automatically turn a detailed script into a narrated explainer with a sequence of illustrated scenes.
Check factual visuals before publishing. In one test of AI-generated scientific explainers, reviewers found Gemini-powered video useful for data visualizations and anatomy walkthroughs. It handled complex physics prompts and camera-angle instructions less reliably. Treat that as a finding from one test, and verify diagrams, measurements, and scene layout yourself using the reported testing results.
Make a narrated explainer with explainroo
explainroo combines a script, spoken narration, and custom-drawn scenes to walk viewers through a topic one step at a time. The kit is free and open source under the MIT license. A coding agent writes script.md, which contains the narration, and scenes.js, the JavaScript code that draws each scene. explainroo then creates an MP4 on your computer.
Start with Claude Code, Codex, Pi, OpenCode, Gemini CLI, or another coding agent that can run shell commands. explainroo works best with Claude Code. Give the agent this prompt, replacing the bracketed topic:
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.
The agent sets up explainroo, creates and checks the video, then gives you the MP4. It uses the open Kokoro voice model to narrate in English and Whisper to match the spoken words to the scene timing. Chrome draws the frames. The kit adds background music and sound effects, and FFmpeg assembles the video.
Before finishing, explainroo provides still images of the scenes and a contact sheet. It also checks for overlapping or cut-off text and misread words. The agent cannot watch the finished video, so review the MP4 yourself too. You can see example videos and read the explainroo documentation.
The kit supports wide, tall, portrait, and square videos. Tall, portrait, and square videos can include word-by-word captions. For a product demo, tell the agent which product to show and share its code or website. The agent can recreate the screens and show a pointer clicking and typing as the narration explains them. explainroo does not edit existing camera footage. It also does not generate talking avatars or live-action scenes, and it has no drag-and-drop editor. Instead, describe the changes you want to the coding agent.
Which option fits your video?
Choose Gemini for a short generated clip, an image animated into a video, or conversational edits to a generated scene. Choose explainroo for a narrated explanation or product walkthrough made from a script and timed scenes.
The explainroo kit costs nothing to use for each video. Optional AI illustrations through OpenRouter cost money per image. The coding agent is a separate service with its own pricing. You can also install explainroo yourself using Node.js, FFmpeg, and Chrome or Chromium.
