Genie 4

DeepMind's real-time world model for interactive scenes, native audio, and language steering.

Also known as Genie 4, Project Genie

What it does

Genie 4 is Google DeepMind's world model, announced October 27, 2026, for real-time interactive simulation. DeepMind says it is natively multimodal, so music, ambient sound, and interactive dialogue are generated with the world, and that you can steer a running scene in natural language, including the weather, the camera, and new people or objects. Keyboard controls cover navigation and the camera. The post says Gemini Omni anchors how a scene looks and behaves, and that Gemini 3.8 Flash can watch the simulation and break a goal into steps. Genie 4 is a research preview for trusted testers. DeepMind says it is coming soon to Google AI Ultra subscribers in Project Genie and to early access partners of the Gemini API and Google AI Studio. Generated video and audio include SynthID. The announcement does not list a price.

Who is Genie 4 for?

Game developers and creators who want to prototype an explorable scene before a broader release.

Tags

• world-model
• games
• audio