Google DeepMind announced Genie 4, which generates ambient sound, music and dialogue alongside interactive scenes that users can steer with natural-language changes to weather, characters and camera position. Gemini-family models observe scenes and coordinate events, with robot and agent training environments also under investigation. Access currently remains a research preview for selected trusted testers; Google AI Ultra subscribers in Project Genie and early Gemini API and AI Studio partners are intended to follow. Realistic demonstrations should not be mistaken for a finished simulator with accurate physics and dependable long-term consistency.