[Google DeepMind Releases Genie 4 World Model with Native Audio and Real-Time Interaction] According to Google's official blog, Google DeepMind announced the release of its next-generation world model, Genie 4, for real-time interactive simulations. Built on the Gemini series, the model utilizes Gemini Omni to make simulated scenes look and behave like the real world. Users can move the camera, change the weather, or add new characters using natural language during scene execution. Each world also generates native audio in real-time, including ambient sounds, music, and interactive dialogue. Genie 4 is currently available to a small group of trusted testers and will be rolled out gradually to Google AI Ultra subscribers in Project Genie, as well as early partners of the Gemini API and AI Studio.