From the source
- Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, giving them first-time access to Genie 4 inside the browser-based world-building prototype.
- Google AI Pro members can join a waitlist on the Project Genie site but are not part of the initial rollout.
- Genie 4 adds mid-session control: users can type prompts while navigating to change weather, add a character or object, move the camera or redirect events without starting over, and the model generates native audio with the visuals, including ambient sound, music and character dialogue.
Google DeepMind describes Genie 4 as natively multimodal, with Gemini Omni providing a real-world reference for how simulations look and behave and other Gemini models supplying reasoning for coherence and continuity.
- The rollout follows Google DeepMind's October 27, 2026 research-preview announcement, which named Ultra subscribers in Project Genie as a next release group.
- Google positions Genie 4 as its higher-fidelity option for visuals, physics and native audio, while Genie 3 remains selectable for longer runs or worlds seeded from 360-degree panorama images; Genie 3's per-generation limit is now three minutes, up from 60 seconds.
- All video and audio generated in Project Genie include SynthID, and Google says both Genie models remain frontier research systems, with camera latency, intricate physical interactions, real-time audio precision and long-term scene permanence unresolved.