GitHub radar
Get a short video with sound from text, free, no install
This is a free web demo running the open MiniMax-H3 model: type a text prompt or give a starting image, and get a short video clip with its own built-in soundtrack, no install, no subscription.
It's a demo page on Hugging Face (a site where you can try AI models right in your browser) where the MiniMax-H3 model turns a text prompt or image into a short video with sound generated together with the picture, not added later.
When it helps
Use it when you want a quick draft clip with sound for a reel or social post without paying for a subscription. Skip it if you need a final-cut-ready video or help writing code.
Pros
- Free to use, no install or subscription needed
- Sound is generated together with the video, not added later
- Works right in the browser from text or an image
- Has a faster Turbo mode for quicker generation
Cons
- Quality trails the best paid video models
- Clips are capped at 5–15 seconds, image up to 768px on the short side
- Doesn't help with code or programming tasks
How to set it up — step by step
- 1Open your AI agent (Claude Code, Codex) in a browser or terminal.
- 2Send the agent the text from the block below, it will explain what the model does.
- 3Open https://huggingface.co/spaces/wank3r/minimax-h3 yourself in a browser.
- 4Write a text description of the video you want, or upload a starting image.
- 5Run the generation and check the finished 5–15 second video with sound.
- 6Turn on the Turbo toggle if you want a faster result.
Text for your agent
Copy this and send it to your agent — Claude Code, Codex, any of them:
Open this demo space https://huggingface.co/spaces/wank3r/minimax-h3 and explain what it does and how to get a short video with sound from my text description.
Nothing to install — it runs in the browser.
Open on Hugging Face▌ More finds