Model Releases
Genie 4: A new generation of world simulation
Genie 4, announced on 27 Oct 2026, is Google’s next‑generation world model that delivers real‑time, photorealistic simulation with native audio and multimodal interaction. Built on the Gemini family—G
Genie 4, announced on 27 Oct 2026, is Google’s next‑generation world model that delivers real‑time, photorealistic simulation with native audio and multimodal interaction. Built on the Gemini family—Gemini Omni anchors realistic appearance while other Gemini models provide reasoning to keep scenes coherent—Genie 4 can simulate dynamic events, reactable sounds, movements, and dialogue for AGI training and new interactive experiences. The model is currently a research preview for trusted testers (including Google AI Ultra subscribers and early Gemini API partners) with a wait‑list available via Project Genie.
Related
- Google announces Gemini 4 and says it’s so capable that only ‘trusted cyber defenders’ can have it right now
- Introducing Gemini Omni
- Google targets AI agents and video generation with Gemini 3.5 Flash and Omni
- Google’s next Genie AI model generates more realistic experiences
Source: Google DeepMind | 2026-10-27