Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
Google DeepMind released Genie 4, a world model with real-time audio, more realistic simulations, and mid-simulation text prompts, in research preview for trusted testers.
TL;DR
- Google DeepMind released Genie 4, a new world model offering photorealistic and interactive simulated worlds.
- Genie 4 generates real-time audio matching the simulated environment, including dialogue and ambient sounds.
- Users can input text prompts mid-simulation to alter scenes, weather, camera angles, or add objects/people.
- The model maintains scene consistency for up to two minutes and features improved physics and character realism.
- Genie 4 integrates with Gemini AI, enabling complex task simulations and potential applications in robotics testing.
- Potential commercial uses include gaming, interactive learning, robotics, and film prototyping.
- Genie 4 is currently available as a research preview for trusted testers, with wider rollout planned.
- Known limitations include potential drift in details over longer simulations and challenges with audio accuracy and text legibility within the simulation.