Google has introduced Genie 4, a new AI model that can create realistic, interactive virtual worlds with sound, natural movements and real-world physics. The model can generate environments that users can explore and change in real time using text prompts and keyboard controls. It can also create background sounds, music-like audio and conversations between characters. Google describes Genie 4 as its “most realistic and interactive world model yet.” Genie 4 is currently being tested with a limited group of users. Keep reading for all the details you need to know.
One of the main features of Genie 4 is its ability to create and modify virtual environments in real time. Users can change elements such as the weather, camera angle and objects in a scene through natural language prompts. The AI adapts these changes to fit the existing environment.
Google says Genie 4 also improves the way virtual characters move and respond to their surroundings. It can simulate physical interactions, including collisions and aerodynamics, while making human movements appear more natural.
Genie 4 is also Google’s first real-time world model that can generate audio natively. “Every world carries the ambient sound of its own setting, from wind in the trees to waves crashing at the beach,” Google said.
“The Genie 4 model incorporates and builds on capabilities from the Gemini family: Gemini Omni anchors the simulations in real-world appearance and behavior, while other Gemini models provide the complex reasoning needed to help maintain a simulation’s coherence and continuity,” it added.
All videos and audio generated using Genie 4 will include SynthID to maintain transparency.
Also read: OpenAI introduces GPT 6.1 Terra AI model, says it excels at communication and computer-based tasks
Excited to share Genie 4 today our most realistic and interactive world model: – steer dynamic environments in real time, shaping events, camera angles, and actions – generate native audio matched to the world, from realistic background sounds to characters who can converse in real time! – simulate photorealistic scenes and real-world physics – create more coherent multi-step events through reasoning from Gemini We’ve started to roll out as a research preview to trusted testers. Coming soon to Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and AI Studio.
— Sundar Pichai (@sundarpichai) October 27, 2026
Google has started rolling out Genie 4 as a research preview to trusted testers. The company plans to make it available to Google AI Ultra subscribers through Project Genie, along with selected early-access partners using the Gemini API and Google AI Studio.
Google is collecting feedback before expanding access to consumers and developers. The company has not announced a wider public release date.