Google DeepMind releases Genie 4 world model in research preview

Google DeepMind released its newest world model, Genie 4, in research preview. The model generates real-time audio matching the simulated world, including music, ambient noises, and interactive dialogue, and allows users to type prompts mid-simulation to change the scene. It also allows freeform edits, such as changing the weather or camera angle in real time or adding new people or objects, and can maintain a consistent scene for up to two minutes, double its predecessor's limit.

Gemini is more closely integrated with Genie 4, acting as the director that plans steps and checks frames while Genie creates the visuals. In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke down tasks into steps that Genie 4 simulated in real time. Google research director Tejas Kulkarni said during a briefing that the future would increasingly feature hybrid world models combining Gemini writing code and text with Genie ingesting that in real time and simulating reality at different levels of abstraction.

The pitched commercial use cases include gaming, interactive learning, and robotics. Google DeepMind engineer Diego Rivas said during a press briefing that the real-time aspect becomes most valuable where keeping a state of flow in the creativity space is useful, such as the ideation and storyboarding phases. Rivas added that users could eventually rely on Gemini Omni, a multimodal large language model that can generate video from images, audio, and text, to turn those prototypes into creative assets, though he said those capabilities are still a ways off.

Rivas stressed that it is still early days for Genie 4 and that it is not yet clear what the end-to-end product experience will be. The team also acknowledged that Genie 4 still has gaps: details and objects can drift the longer a simulation runs, and they still have not quite figured out how to ensure the audio will be accurate and any in-world text will be legible.

Genie 4 is available now as a research preview for trusted testers. In the coming weeks, the model will roll out to Google AI Ultra subscribers in Project Genie, Google's AI tool for generating interactive worlds from text or image prompts, and to early access partners of the Gemini API and Google AI Studio.