October 27, 2026
Google Unveils Genie 4 With Interactive AI Worlds and Real-Time Audio [Video]

Google Unveils Genie 4 With Interactive AI Worlds and Real-Time Audio [Video]

Posted 41 minutes ago by

Google DeepMind has unveiled Genie 4, a new AI model that generates interactive worlds users can explore and change as they go. The update adds native sound and dialogue alongside text controls for changing a scene in real time.

Google DeepMind Genie 4 announcement artwork featuring a hummingbird
Image: Google DeepMind.

Rather than producing a fixed video, the model responds as users navigate with keyboard and camera controls. A text prompt can change the weather, introduce a person or object, or adjust the camera, with Gemini helping fit those changes into the surrounding scene.

Sound is generated along with the visuals, from wind and waves to music and spoken conversations. Characters can react to events and user input while the simulation continues. Google also claims improved physics and more natural human movement.

Behind the scenes, Gemini 3.8 Flash acts as a guiding agent. It watches incoming frames, breaks goals into steps, and checks whether those steps succeeded before adjusting its plan. The company is also experimenting with Gemini 4 Argon and its robotics research to simulate tasks that unfold across multiple stages.

Genie 4 simulation of a silk ribbon moving in the wind, with reasoning steps and navigation controls
A generated scene from Google's Genie 4 silk-scarf demo. Image: Google DeepMind.

Early testers are exploring uses beyond entertainment. Filmmakers can try camera angles, lighting, dialogue, and action before shooting a scene. Game developers can test an interactive concept before writing engine code, while researchers can generate scenarios for training robots and AI agents.

The technology is still experimental. Visual details can drift during longer sessions or after complex edits, and objects may not remain consistent as users move around. Physics, audio accuracy, readable text, and spatial accuracy are also unfinished. Generated video and audio will carry Google's SynthID watermark to help identify them as AI-created.

For now, access is limited to trusted testers. A wider preview is coming to Google AI Ultra subscribers through Project Genie and to early-access partners through the Gemini API and Google AI Studio. Google has opened a waitlist but has not announced a date for that rollout.

Add Comment
Would you like to be notified when someone replies or adds a new comment?
Yes (All Threads)
Yes (This Thread Only)
No
iClarified Icon
Notifications
Would you like to be notified when we post a new Apple news article or tutorial?
Yes
No
Comments
You must login or register to add a comment...
Recent. Read the latest Apple News.
RECENT
Tutorials. Help is here.
TUTORIALS
How To Turn Off iPhone [Video]
How To Back Up Your iPhone to an External Drive on Mac [Video]
Where To Download iPad Firmware Files From
How To Find Your IP Address on iPhone [Video]
Where To Download iPhone Firmware Files From
Deals. Save on Apple devices and accessories.
DEALS