Google has released Genie 4, a new world model designed to generate interactive virtual environments. The model leverages the Gemini 3.8 Flash architecture to enhance simulation logic and interaction performance.
Key upgrades include improved visual realism, real-time scene modification via natural language prompts, and automated audio generation. The model can now produce interactive experiences lasting up to two minutes, doubling the duration supported by the previous version.
The technology is intended for applications in game development, film pre-visualization, and robotics training. It allows users to test spatial relationships and physical constraints within a simulated environment without the need for physical assets.
Genie 4 is currently available as a research preview for selected testers. Google has opened a waitlist for Project Genie, with future access planned for Google AI Ultra subscribers.
