Google DeepMind releases Genie 4 world model with real-time updates and audio
The short version
- Genie 4 is a world model developed by Google DeepMind for generating interactive experiences.
- The model supports real-time updates using natural language prompts during simulation.
- It includes audio generation capabilities for more immersive environments.
- Genie 4 uses Gemini 3.8 Flash as its underlying AI model.
- The model is currently in research preview for trusted testers.
Does this story matter to you?
Coverage compared
How coverage grew
First reported by The Verge Google’s next Genie AI model generates more realistic experiences
Ars Technica DeepMind unveils Genie 4 world model promising more realistic physics and humans
TechCrunch Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
All 3 articles
- TechCrunch, left-leaningGoogle’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
- Ars Technica, left-leaningDeepMind unveils Genie 4 world model promising more realistic physics and humans
- The Verge, left-leaningGoogle’s next Genie AI model generates more realistic experiences