Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs
Real-time world model generates sound and dialogue, limited to testers
New model
Google Deepmind has introduced Genie 4, an interactive world model that calculates environments frame by frame in real time and, for the first time, directly generates matching background audio and character dialogue.
The model is the successor to Genie 3, which the company showed in August 2025, and it does not produce finished videos: users move through the scene with the keyboard and steer events with text prompts.
According to Deepmind, each world has its own background audio, such as wind in the trees, and characters are supposed to talk to each other and react in real time to user input or events.
Gemini models plan in the background to keep the world coherent, with Gemini 3.8 Flash watching the scene continuously, breaking a goal into steps, and using new frames to check whether each step worked.
Deepmind calls Genie 4 an early, experimental model: the world stays consistent over short sessions, but visual details can shift and objects don't always persist in longer simulations or after several complex prompt changes.
For now it is only available to select testers as a research preview, and is set to reach Google AI Ultra subscribers in the Project Genie web app soon, along with partners who have early access to the Gemini API and Google AI Studio.
Google says all videos and audio tracks will carry its SynthID watermark, which invisibly marks AI-generated content.
From the source
Google Deepmind has introduced Genie 4, an interactive world model that calculates environments frame by frame in real time and, for the first time, directly generates matching background audio and character dialogue.
Gemini models steer events in the background, planning multistep tasks and continuously adapting the simulated world to user text prompts and changing conditions.
Genie 4 is still an experimental research model with limitations in longer sessions and complex physics. Access is limited to select testers for now and will later expand to Google AI Ultra subscribers.
Genie 4 is supposed to simulate interactive worlds in real time, including sound and talking characters. Gemini models plan in the background what happens next in the simulation. Only select testers can try the world model for now.
Google Deepmind has introduced Genie 4 , the successor to Genie 3 , which the company showed in August 2025. The world model doesn't produce finished videos but calculates a scene frame by frame, reacting to input as it goes. Users move through the scene with the keyboard and steer events with text prompts.