Live updates
Google opens Genie 4 world model to AI Ultra subscribers: type a new prompt mid-walk and the world changes, with sound and dialogue
First seen on X 18 hours ago@GoogleDeepMind ♥ 96832 views
Google DeepMind has opened Genie 4, the world model it previewed for trusted testers last month, to Google AI Ultra subscribers. Type a new prompt while exploring a generated world and the environment changes in real time, from shifting weather to a new character, with native audio and dialogue generated to match the scene.
According to a Google blog post on Nov 18, Genie 4 is available in Project Genie, the experimental service for generating and walking through interactive worlds in the browser. Google calls it "our most realistic and interactive world model yet." A new Project Genie agent lets users build worlds through conversation: describe a vision and the agent orchestrates Google's multimodal models to set the world's look and a custom soundtrack, while Gemini watches the screen during exploration to suggest where to go next or trigger in-world events. A community gallery lets people publish and remix worlds; "The Life of Ants," made with filmmaker Anand Gandhi, lets you navigate a colony from an ant's perspective. Genie 3 sessions now run up to 3 minutes per generation, up from 60 seconds, and can chain multiple worlds or start from 360-degree panorama images. Google AI Pro members can join a waitlist starting the same day. Google lists camera latency, intricate physical interactions, real-time audio precision and long-term scene permanence as open challenges, and says all generated video and audio carries SynthID watermarks.
Comments 0
Select a sentence in the story (long-press on phones) to comment on it.
“Genie 4 is now available in Project Genie. It brings native audio, real-time editing, and a new agent to help you create interactive, virtual worlds.”

