Announcing Genie 4, A New World Model for Real-Time Interactive Simulation
Google, Tuesday, October 27th, 2026
Google DeepMind announces Genie 4, a world model for real-time interactive simulation with native audio and natural language control.
Google announced research on Genie 4, a world model that brings greater realism and native audio to real-time interactive simulation.
It builds on the Gemini family, with Gemini Omni grounding simulations in real-world appearance and behavior and other Gemini models helping maintain coherence.
Users can steer scenes in real time with natural language, such as moving the camera, changing the weather or adding characters, while worlds generate ambient sound, music and dialogue.
Genie 4 is rolling out to trusted testers and is coming to Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and AI Studio.