AI BriefingGoogle announces Genie 4, a world model for real-time interactive simulation with native audio
·2026.10.28 01:00
Key point
The model uses Gemini Omni for realism and other Gemini models for reasoning, allowing users to steer scenes and generate ambient sounds and dialogue on the fly.
Details
- Google DeepMind announces Genie 4, a new world model designed for real-time interactive simulation with unprecedented realism and native audio generation.
- Users can steer scenes in real time using natural language commands to move cameras, change weather, or introduce characters, while the model generates ambient sounds, music, and interactive dialogue on the fly.
- Genie 4 builds on the Gemini family, utilizing Gemini Omni to anchor simulations in real-world appearance and behavior, while other Gemini models provide the reasoning necessary to maintain simulation coherence and continuity.
- The model is currently rolling out to a limited group of trusted testers, with upcoming availability for Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and AI Studio.
- The technology aims to support safe training environments for robots and agents and amplify creative tools in industries including filmmaking, journalism, gaming, and manufacturing.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Google DeepMind Establishes 'DeepMind Institute' for AGI Era Research and DiscussionThe Next Chapter of AI Momentum