Google DeepMind Introduces Genie 4 for Interactive World Simulation

Google DeepMind has introduced Genie 4, a world model that generates interactive environments with real-time audio and lets users steer scenes through prompts. The system is available as a research preview for trusted testers, with broader access planned through Project Genie and developer channels. Google DeepMind says Genie 4 builds on Gemini models: Gemini Omni anchors simulations in real-world appearance and behavior, while other Gemini models help maintain reasoning, coherence, and continuity. Users can describe environments and events, then make live changes such as moving the camera, adding characters, or changing the weather.