Google DeepMind has unveiled Genie 4, a new world simulation model that enhances realism and real-time interactivity. This natively multimodal model integrates audio generation, including ambient sounds and interactive dialogue, alongside visual simulation. Genie 4 builds upon Google's Gemini family of models, with Gemini Omni providing real-world appearance and behavior anchoring, and other Gemini models offering reasoning for simulation coherence. The model is currently in a research preview for trusted testers and will be rolled out to Google AI Ultra subscribers and early access partners of the Gemini API and Google AI Studio. AI
IMPACT Enhances realism and interactivity in world simulations, potentially accelerating development of agents and interactive experiences.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- Gemini
- Gemini 3.8 Flash
- Gemini 4 Argon
- Gemini API
- Gemini Omni
- Google AI Studio
- Google AI Ultra
- Google DeepMind
- Project Genie
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →