Google opens Genie 4 to Ultra subscribers: What is it?
What's the story
Google has launched its latest world model, Genie 4, for eligible AI Ultra subscribers. The new feature is part of Project Genie, a browser-based experiment for creating interactive environments. With this launch, users can create immersive digital worlds that they can walk through and modify with text prompts. The model also lets you populate these worlds with characters that respond to user interactions.
Enhanced capabilities
It generates visuals and sound as you explore
Genie 4 creates the scene as users explore it.
This means you can give instructions in the middle of a session to change elements like weather or introduce characters without starting over.
Plus, it generates sound along with visuals, creating an immersive experience with everything from wind and footsteps to dialogue that reacts to events in the scene.
Subscription model
Genie 4 is available for AI Ultra subscribers
The new feature is available as part of the Google AI Ultra subscription, which costs $199.99 per month in the US.
While eligible Ultra users can access this experience immediately, AI Pro subscribers will have to join a waitlist for access.
This marks a major step in Google's journey with Project Genie, which started as side-scrolling experiments back in 2024.
Technological advancement
Project Genie has evolved rapidly over the years
The first version of Genie learned from over 200,000 hours of gameplay footage and could turn a single image into a simple playable 2D environment.
Later, Genie 2 took the research into three-dimensional spaces, allowing people or AI agents to navigate generated environments with keyboard and mouse controls.
Now, Google is keeping Genie 3 available alongside the new model, with sessions extended to three minutes and support for 360-degree panorama images.