In October 27, 2026, Google DeepMind officially released the new world model Genie4, marking a new stage in real-time interactive simulation technology.
The model combines an unprecedented sense of realism with native audio in real-time interactive simulations. By integrating the core capabilities of the Gemini series, Gemini Omni anchors the simulation in the appearance and behavior of the real world, while other Gemini models provide complex reasoning support to ensure the coherence and continuity of the simulation.
In terms of technical features, Genie4 allows users to start events and control scenarios in real time, including dynamic camera movement, changing weather conditions, or introducing new characters. Each simulated world can generate native audio instantly, including environmental sounds, background music, and interactive dialogues, which greatly enhances the immersion and realism of the interaction.
As a key milestone on the path to general artificial intelligence, this model not only provides safe virtual training environments for robots and agents, but also injects efficient innovation tools into diverse industries such as film production, news dissemination, game development, and manufacturing.
Currently, Genie4 has been made available to some trusted testers, and will be gradually offered to Google AI Ultra subscribers (through Project Genie) as well as early access partners of the Gemini API and AI Studio, further promoting the commercialization and ecosystem implementation of cutting-edge simulation technologies.