Google CEO Sundar Pichai recently announced the launch of Project Genie, a new AI-powered web app from Google that allows users to create and explore interactive virtual worlds. The tool is currently available as a prototype and is rolling out to AI Ultra subscribers in the United States.
Calling the experience ‘out of this world,’ Pichai shared details about Project Genie on Elon Musk-owned social media platform X, saying the app lets users build their own digital environments using advanced AI models.
“Project Genie is a prototype web app powered by Genie 3, Nano Banana Pro + Gemini that lets you create your own interactive worlds. I’ve been playing around with it a bit and it’s…out of this world. Rolling out now for US Ultra subscribers,” Pichai wrote.
How To Check Which Websites Share Your Data With Instagram And Facebook: Check This Simple Step-By-Step Guide
Project Genie is powered by Genie 3 along with Nano Banana Pro and Gemini. It is designed to turn simple text prompts or images into interactive worlds that users can explore in real time. The tool was earlier available only as a limited research preview but it is now being tested with real users through this web app.
In a short demo shared by the Google CEO, an astronaut can be seen moving inside a space station. This was created entirely using the AI tool.
How Project Genie Works
To Create a world in Project Genie, you need to use a feature called World Sketching. Like other tools, users can write a short description of a scene or upload an image. The AI will create a world with characters and objects based on your input. After the world is created, users can explore it in first-person or third-person view.
As they move around, the AI updates the environment in real time..
However, each session is limited to 60 seconds. The tech giant has warned that some worlds may not look fully realistic and users might face slight delays in character movement.
Who Can Use It?
At present, Project Genie is only available to Google AI Ultra subscribers in the US. According to Google DeepMind’s Diego Rivas, the tool is experimental and is mainly meant to understand how people use AI-generated worlds and what new use cases may emerge.
Google believes that learnings from Project Genie could also help robots understand and navigate real-world spaces in the future.
