Genie 4 is a world model that Google DeepMind announced on October 27, 2026, calling it its most realistic and interactive world model yet. You set an event in motion and Genie 4 simulates what happens next: how the world responds, how it sounds, and how the people in it move, react and speak.
It is natively multimodal, so music, ambient noise and interactive dialogue are generated together with the world, and the sound in the demo videos comes directly from Genie 4. You can also steer a scene in real time with natural language, for example moving the camera, changing the weather or adding new characters.
Genie 4 builds on the Gemini family. Gemini Omni anchors the simulation in real world appearance and behavior, while other Gemini models provide the reasoning needed to keep it coherent over time. Google DeepMind lists uses such as training environments for robots and agents and creative tools for film, journalism, gaming and manufacturing.
Genie 4 is currently a research preview for trusted testers. Google DeepMind says it is coming soon to Google AI Ultra subscribers in Project Genie and to early access partners in the Gemini API and Google AI Studio, and there is a waitlist for anyone who wants to try it.