Generative AI
Oct 27, 2026
Google DeepMind unveils Genie 4 world model with enhanced realism and audio features
Oct 27, 2026
AI Summary
Google DeepMind has launched Genie 4, a new world model that offers photorealistic visuals and real-time audio, allowing users to interactively modify simulations. This release follows a trend of consolidation in the world model industry and aims to enhance applications in gaming, interactive learning, and robotics.
- Google DeepMind released Genie 4, a world model that generates photorealistic and interactive environments with real-time audio. Users can modify scenes mid-simulation, including weather changes and camera angles.
- Genie 4 can maintain a consistent scene for up to two minutes and features improved physics and human-like characters. It integrates closely with Google's Gemini AI model, which helps plan and check simulation steps.
- The model is positioned for various applications, including gaming, interactive learning, and robotics, with potential uses in film prototyping highlighted by trusted testers.
- Genie 4 is currently available as a research preview for selected testers, with plans for broader rollout to Google AI Ultra subscribers and early access partners in the near future.
- The model's development reflects ongoing trends in the world model industry, including acquisitions and the emergence of hybrid models that combine different AI capabilities.
googledeepmindworld modelaudiorealistic simulations