Google DeepMind has released Genie 4, its newest AI world model, in research preview — a system that generates photorealistic, interactive worlds with real-time audio and lets users steer the simulation as it runs.
Google Genie 4 (Credits: TechCrunch)
Announced on Tuesday, Genie 4 is Google’s most advanced world model yet. Users can type prompts mid-simulation to change the scene, from shifting the weather or camera angle to adding new people and objects on the fly.
Google Genie 4 Adds Real-Time Audio and Two-Minute Scenes
The headline upgrade is audio. Genie 4 generates real-time sound that matches the simulated world, including music, ambient noise, and interactive dialogue. It also keeps a scene consistent for up to two minutes — double the limit of its predecessor, Genie 3, which launched as a research preview a little over a year ago.
The new model also brings better physics and more human-like characters, making its worlds feel more believable than ever before.
Gemini Acts as Director Inside Genie 4 Worlds
Google’s Gemini model is now more closely integrated with Genie 4, acting as a director that plans steps and checks frames while Genie creates the visuals. In a research experiment tied to Gemini Robotics, a model broke down tasks into steps that Genie 4 simulated in real time — pointing to a future where robot scenarios can be tested in simulation before they happen in the real world.
“What we’ll increasingly see in the future are these hybrid world models, where you have a combination of Gemini writing code and text, and Genie ingesting that in real time and simulating reality at different levels of abstraction,” said Tejas Kulkarni, research director at Google.
The pitched uses span gaming, interactive learning, and robotics, while early testers are already pointing to film prototyping — using real-time worlds for rapid storyboarding and ideation.
Genie 4 is not without gaps. Google acknowledged that details and objects can drift the longer a simulation runs, and that audio accuracy and legible in-world text remain unsolved problems. The model is available now as a research preview for trusted testers, with a rollout to Google AI Ultra subscribers in Project Genie coming in the next few weeks.
Also Read: Meta AI Director Rohit Patel Leaves to Take on Microsoft Office and Google Workspace With Ndoc
Source: TechCrunch — read the full story there.
