Gemini-Powered Genie 4 Builds Real-Time Worlds With Sound and Talking Characters

On October 27, 2026, Google DeepMind announced Genie 4, its newest world model: an AI system that generates interactive environments in real time that you can move through and change as they run.

Built on Gemini

DeepMind says Genie 4 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 reasoning that helps keep a simulation coherent.

To do this in real time, DeepMind says Gemini 3.8 Flash acts as a guiding agent in the loop. As Genie 4 generates a world, Gemini watches the scene, breaks a goal into a sequence of steps, and reviews incoming frames to check that each step succeeded. DeepMind also showed Gemini 4 Argon and Genie 4 working together to simulate Apptronik’s Apollo humanoid robot playing checkers.

Worlds with sound

DeepMind calls Genie 4 its first real-time world model to generate audio natively. Each world carries the ambient sound of its setting, from wind in the trees to waves at the beach, and Genie 4 adds interactive dialogue: characters converse and react to your inputs or to events in the world.

Users navigate with standard keyboard controls and steer with text prompts, for example changing the weather, moving the camera, or introducing a new person or object, and Gemini adapts the prompt to fit the scene. DeepMind also highlights improved photorealism and more natural simulation of physics and people.

Who can use it

Genie 4 is rolling out first as 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, with a waitlist open now. All video and audio Genie 4 generates will carry SynthID watermarks.

Limits

DeepMind calls Genie 4 an early, experimental model. It says visual details and object permanence can still shift or drift over time, especially in longer sessions, after many prompt edits, or while moving around a scene. Complex physical interactions, real-time audio accuracy, legible text and long-term consistency are still being worked on.