Google DeepMind Announces Genie 4: A New Generation of Natively Multimodal World Simulation
Google DeepMind has unveiled Genie 4, a new world model enabling real-time interactive simulation with native audio and dialogue generation, currently in research preview.
On October 27, 2026, Google DeepMind officially announced the launch of Genie 4, its new generation world model designed to unlock unprecedented realism and improve real-time interactive simulation. Unlike previous models focused primarily on visual generation, Genie 4 is natively multimodal, capable of simultaneously generating audio-like music, ambient noises, and interactive dialogue that match the simulated world.
The Genie 4 model builds on capabilities from the Gemini family. Specifically, Gemini Omni anchors the simulations in real-world appearance and behavior, while other Gemini models provide the complex reasoning needed to maintain the simulation's coherence and continuity. Users can 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.
Google DeepMind stated that understanding and simulating the world is a crucial aspect of building AGI. Genie 4 advances the ability to create safe, infinitely variable simulations that can help with everything from developing training environments for robots and agents to unlocking the creation of new interactive experiences. The model introduces a new standard of realism in physics and human action, simulating scenarios like aerodynamics and collisions, and creating characters that move naturally, respond organically to their environments, and can be interactively steered in real-time.
Currently, Genie 4 is being rolled out as a research preview for trusted testers to gather feedback before a wider release to consumers and developers. Early access is starting with Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio.