Genie 4 is now available in Project Genie. Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, opening first-time access to Genie 4, its most realistic and interactive world model yet, alongside upgrades to Genie 3, a Project Genie agent and a community gallery. Google AI Pro members can join the waitlist on the same page.
With Genie 4 you can prompt mid-session to change the world you created — type a new prompt while navigating and edit environments in real time, shifting the weather, dropping in a character or redirecting the action. For the first time, Genie 4 pairs its visuals with real-time native audio that adapts as the scene unfolds, from ambient soundscapes to character dialogue.
Genie 3 remains available in the model picker for longer runs or panorama-seeded spaces, with sessions extended to up to 3 minutes per generation, up from 60 seconds, world chaining to link multiple worlds together, 360-degree panorama image grounding, and real-time in-world events driven by natural-language prompts.
The new Project Genie agent builds worlds from conversation: describe your vision in natural language and it orchestrates Google's multimodal models to craft the world's look and a custom background score. Gemini models can join a session as you explore, observing the screen, surfacing suggestion chips or triggering in-world events. A community gallery gathers curated worlds and community creations — turn personal photos into explorable spaces in Living Memory, explore prehistoric habitats in Dino Field Guide, or play Rock Paper Scissors with Gemini as referee — plus collaborations Villa Giallo and The Life of Ants. All generated video and audio carries SynthID watermarking, and inputs and outputs go through safety screenings.




