Latest: Google DeepMind Launches Genie 4 Real-Time World Model With Native Audio
Genie 4 extends AI-generated media from passive video to interactive, steerable simulation with audio, which DeepMind identifies as relevant to robotics training, game prototyping, and film pre-visualization. Google acknowledged that physics and spatial details can be inconsistent over longer sessions.
When stories like this move, I write about them in an email each morning.
One free email each morning, around 8 AM US Eastern.
I have sent you a confirmation link. One click and you are in.
Not in your inbox? Look in spam or promotions. If it's there, mark it "Not spam" so future editions land in your inbox.
Google DeepMind released Genie 4, its most realistic and interactive world model, on October 27, 2026. The model generates interactive environments frame by frame in real time without pre-rendered assets or hand-programmed interactions. It is the first in the Genie line with native audio, producing ambient sound, music, and live dialogue from characters that react to users and in-world events. Simulations run up to two minutes, double the one-minute ceiling of Genie 3.
The architecture pairs Gemini Omni, which anchors simulations in real-world appearance, with Gemini 3.8 Flash acting as an in-loop director that breaks goals into steps and checks incoming frames to maintain coherence. Users can modify a running simulation in real time by typing commands to change weather, move the camera, or add people. DeepMind described the improvement to human simulation as the most dramatic leap, with characters that move naturally, respond organically to their environments, and can be interactively steered. In one demonstration, Gemini 4 Argon used the Genie 4 loop to simulate Apptronik's Apollo humanoid robot playing checkers.
Access is rolling out via Project Genie to Google AI Ultra subscribers in the U.S. who are 18 or older; the prototype is not available to Google AI Ultra for Business users. Google plans to expand to more territories and to Gemini API early access partners over time. All generated video and audio includes SynthID digital watermarking.
Project Genie opened to Google AI Ultra subscribers in the U.S. on or around November 1, moving Genie 4, Google DeepMind's real-time interactive environment generator announced October 27, from trusted-tester preview to a broader consumer rollout.
Import AI's November 2 coverage added detail on Gemini 3.8 Flash's role inside the simulation as a continuous observe-plan-verify loop that breaks goals into steps and reviews each incoming frame.
Import AI newsletter covers Genie 4 launch, noting Gemini 3.8 Flash integration for multi-step reasoning
Weekly AI newsletter notes Genie 4 release and that it impressed Ethan Mollick
Coverage published October 28 added that Google has acknowledged inconsistencies in physics and spatial details over longer sessions of Genie 4, the real-time interactive environment generator it announced October 27, and named film pre-visualization and game-level prototyping as additional potential applications.
One outlet described Genie 4 as a shift from AI that produces finished media to AI that generates interactive experiences.
Google DeepMind announced Genie 4 on October 27, 2026, a real-time interactive world model that generates environments frame by frame with native audio, including ambient sound, music, and live character dialogue.
Gemini Omni anchors visual realism and Gemini 3.8 Flash acts as an in-loop director breaking goals into steps. Simulations run up to two minutes, double the one-minute limit of Genie 3, and users can modify running simulations by typing commands. Access is rolling out through Project Genie to U.S. Google AI Ultra subscribers aged 18 and older, not to Business users, with expansion to more territories and Gemini API early access partners planned.
Project Genie rolls out to Google AI Ultra subscribers in the U.S. (18+), not available to Google AI Ultra for Business users
BackgroundFrontier models, open models, and how they are compared
When stories like this move, I write about them in an email each morning.
One free email each morning, around 8 AM US Eastern.
I have sent you a confirmation link. One click and you are in.
Not in your inbox? Look in spam or promotions. If it's there, mark it "Not spam" so future editions land in your inbox.