A Guth Labs publication ↗
Back to News

Google brings Genie 4 to AI Ultra subscribers in Project Genie

Miniature forest landscape and stream inside a hovering glass sphere with gold ripple arcs above a cream pedestal.
AI-generated editorial illustration

Google began rolling out Genie 4 in Project Genie to eligible Google AI Ultra subscribers on November 18, alongside a creation agent and community gallery, according to its announcement.

The browser-based experience lets users explore generated worlds and change them mid-session with text prompts, such as altering the weather or adding a character. Genie 4 generates native audio that responds to the scene, including ambient sounds and dialogue.

The update also expands Genie 3, which remains selectable. Its sessions can now last up to three minutes per generation, compared with 60 seconds previously. Users can connect worlds, start from 360-degree panorama images and prompt events while exploring.

A new Project Genie agent coordinates Google’s models to help create initial scenes and background music through conversation. The gallery lets users explore, publish and remix worlds.

Google AI Pro members can join a waitlist rather than receiving immediate access. Google says generated video and audio carry SynthID watermarks, while limitations remain around latency, physical interactions, audio precision and scene consistency.

The rollout moves Genie 4 beyond its earlier trusted-tester preview without making it a generally available developer API.

Sources and citations

Revision history

Published .