Google DeepMind releases Genie 4, a world model with audio and live edits
The research preview can hold a scene for about two minutes and accepts prompts while the simulation is running.
Google DeepMind released Genie 4 in research preview on Tuesday, TechCrunch reported. The model generates interactive worlds with matching audio, including music, ambient sound and dialogue, and lets a user type prompts during a simulation to change the scene, such as the weather, the camera or the people in it. Google said it can keep a consistent scene for up to two minutes, twice the limit of Genie 3, which was released as a research preview a little over a year ago.
TechCrunch noted a crowded field. Runway released a second world model, GWM Worlds 2, a couple of months earlier. Fei-Fei Li's World Labs is being acquired by AMD, Amazon is in talks to buy Decart, and Rivian just acquired Third Dimension for simulation work.
From ARQS Sponsored
On the practical side, West Coast companies can turn to Design Workbench, TradeHound, Website audit and Flow automation. In the ARQS Store, Wine Cellar Ledger — 1 Month Access, ARQS ContractDiff Desk, SponsorKit — Creator Media Kit & Rate Card Builder are among the newest tools available.
- ROI Intelligence
- Business network
- Advertise with ARQS
- AI chatbot hosting
- Website packages
- Reputation engine
- Resume service
- ATS resume optimizer
- Software marketplace
- Developer platform
- AI Academy Year 1 — Foundations Agentic AI Systems
- AI Academy Year 1 — Foundations No-Code AI Development
- AI Academy Year 1 — Foundations Business Process Automation