Google DeepMind Releases Genie 4: A Real-Time World Model With Native Audio
Google DeepMind has released Genie 4 as a research preview for trusted testers. The Genie 4 world model generates explorable worlds from text and image prompts in real time. It also produces a full soundscape: ambient noise, music, and character dialogue. Users navigate with keyboard controls and steer events through plain-language prompts.
The bigger shift is architectural. A Gemini model now runs inside the simulation loop as a planner, a pattern that matters for anyone building training environments for agents or robots. The release arrives as world models become a serious frontier for embodied AI in 2026, with simulation-based agent training moving from research curiosity to production pipeline.
TL;DR
- Runs on: Google-hosted only (Project Genie web app, Gemini API early access).
- Performance: Photorealistic worlds with native audio and live text steering.
- Best: Scene consistency for up to 2 minutes, double that of Genie 3, per TechCrunch's briefing.
- Worst: Sessions last a few minutes, and objects drift after repeated prompt edits.
What Is Genie 4?
Genie 4 is a world model from Google DeepMind that simulates interactive environments frame by frame. It is not a video clip generator. Each frame responds to user input as it arrives, meaning the world evolves in direct reaction to what the player or agent does rather than playing back a pre-rendered sequence.
via MarkTechPost