Google DeepMind announced Genie 4, a new world model that unlocks unprecedented realism and real-time interactive simulation. The natively multimodal model simultaneously generates audio-like music, ambient noises, and interactive dialogue with the world. Built on the Gemini family, Gemini Omni anchors simulations in real-world behavior, while other Gemini models provide complex reasoning for coherence.
Users can set events in motion, and Genie 4 simulates world responses, character movements, reactions, and speech. The model advances capabilities for developing robot training environments and creating new interactive experiences. DeepMind is rolling Genie 4 out as a research preview for trusted testers, starting with Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio.
A waitlist is available for Project Genie. Genie 4 delivers enhanced photorealism, fluid movement, and native audio. Key capabilities include real-time world modification via natural language, advanced physics simulations including aerodynamics and collisions, characters that move naturally and respond organically, and native generation of ambient sounds and interactive dialogue.
Gemini 3.8 Flash serves as a guiding agent, observing the scene, breaking down goals into steps, and tracking progress in real-time. As the world shifts or users intervene, Gemini adapts its plan, unlocking worlds with reliable causality, procedural behaviors, and multi-step reasoning. DeepMind is also experimenting with Gemini 4 Argon and Genie 4 to bring frontier research together with Gemini Robotics.
Source: Google DeepMind Blog · Summarized by HeadlinesBriefing