Genie 4: Google DeepMind's world model now generates sound and dialogue, in research preview
What is it?
Genie 4 is a world model: it generates a 3D scene in real time that you can move through with the keyboard. This version produces ambient sound, music and character dialogue in the same pass as the video. You can type instructions mid-simulation, like changing the weather or adding a person or object. Gemini Omni handles realistic appearance and motion, while other Gemini models keep the scene coherent over time.
Why does it matter?
The main use is generating endless, varied training environments for robots and for agents that operate screens. Google says early Gemini API and AI Studio partners will get access, which could make this the first time teams building games, simulations or agent test beds can use Genie through an API. Google itself notes that objects and details still drift in longer sessions.
Maturity
ResearchResearch preview for trusted testers only. Access for Google AI Ultra subscribers and API early-access partners has no date yet, though there is a waitlist.
How to track it
- API access: watch the Gemini API docs and Logan Kilpatrick's X posts for a Genie 4 API date.
- Project Genie: look for the Google AI Ultra rollout on the Google DeepMind blog.
- Consistency: follow independent demos and reviews to see how long objects stay stable in longer sessions.