From the source
Google DeepMind is announcing research on Genie 4, a world model that adds native audio and real-time interactive simulation, and has begun rolling it out to a limited group of trusted testers.
- The model builds on capabilities from the Gemini family, with Gemini Omni anchoring simulations in real-world appearance and behavior while other Gemini models supply the reasoning that helps maintain a simulation's coherence and continuity.
- Users can set an event in motion and steer scenes in real time with natural language, moving the camera, changing the weather or introducing new characters, and every world generates audio on the fly, including ambient sounds, music and interactive dialogue.
- DeepMind says simulating the world is a crucial step toward AGI, enabling safe training environments for robots and agents and amplifying creative tools in filmmaking, journalism, gaming and manufacturing.
- Genie 4 is coming soon to Google AI Ultra subscribers in Project Genie and to early access partners in the Gemini API and AI Studio.
