Audience
AI researchers, robotics engineers, autonomous agent developers, game developers, filmmakers, visual effects artists, simulation engineers, educators, creative technologists, and organizations seeking real-time AI-generated environments, interactive world simulation, physics modeling, and virtual training experiences
About Genie 4
Genie 4 is a generative AI world model developed by Google DeepMind that creates realistic, interactive virtual environments in real time. The model generates explorable worlds with dynamic visuals, native audio, physical interactions, and responsive human characters. Users can navigate generated environments using keyboard controls and modify scenes through natural language instructions, including changing weather conditions, moving cameras, and introducing objects. Its physics simulation capabilities model phenomena such as aerodynamics, collisions, and natural human movement. Genie 4 integrates with Google's Gemini models to support complex reasoning, multistep event simulation, and interactive environments that respond coherently to user actions. The model is available as a limited research preview for trusted testers, with planned access through Project Genie, Google AI Studio, and the Gemini API.
Company Information
Videos and Screen Captures
