Google Launches Genie 4 Research Preview With Native Audio and Longer Interactive Worlds

Google DeepMind released Genie 4 in research preview on Tuesday, adding synchronized real-time audio, more photorealistic worlds, and scene changes through prompts during simulations. It maintains consistent scenes for up to two minutes, double Genie 3’s limit, though objects can drift and audio accuracy and text legibility remain challenges. Trusted testers have access now, with rollout to Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio planned in the coming weeks.

Sundar Pichai introduced Genie 4 as Google's most realistic and interactive world model, with real-time control over environments, native audio including conversational characters, photorealistic scenes, and real-world physics simulation. It uses Gemini reasoning for more coherent multi-step events. A research preview has begun rolling out to trusted testers, with access coming soon to Google AI Ultra subscribers in Project Genie and early access partners through the Gemini API and AI Studio.

Introducing Genie 4 from @GoogleDeepMind, which Google AI describes as its most realistic and interactive world model yet 🌍 Users can use natural language to dynamically steer the world and its soundscape in real time, including changing the weather, moving the camera, or introducing new elements. https://t.co/ZfZGi9Chsx

Google DeepMind introduces Genie 4 as its most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak. https://t.co/6mmSUm9BBO

Google DeepMind has released Genie 4 as a research preview for trusted testers, adding native audio, interactive dialogue, and real-time natural-language steering to world simulation. Gemini 3.8 Flash guides multi-step events by observing scenes, planning actions, and checking progress. Access is coming soon to Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and Google AI Studio; object permanence, physical interactions, and long-term consistency remain research challenges.

Google DeepMind has unveiled Genie 4, an updated world model that improves on Genie 3 in almost every way, including more realistic physics and humans. The model generates virtual worlds frame by frame in real time as users explore them, and DeepMind says the technology could provide training environments for physical robots or support rapid prototyping in creative fields.

Google announced Genie 4, a world model that it says generates more realistic interactive experiences, supports real-time natural language updates, generates audio, and uses Gemini 3.8 Flash for simulations. Experiences can last about two minutes, up from one minute with Genie 3, though details and object permanence can shift over time. It launches as a research preview for trusted testers, with Google AI Ultra access coming soon and a waitlist for Project Genie.