Google DeepMind Unveils Genie 4: A Revolutionary Real-Time World Model with Native Audio Capabilities

AI News

Google DeepMind Unveils Genie 4: A Revolutionary Real-Time World Model with Native Audio Capabilities

Google DeepMind Genie 4 World Model Adds Audio

10/28/2026

Google DeepMind's Genie 4 world model adds native audio and lets testers steer photorealistic scenes with text prompts in real time.

MarkTechPost

Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio

10/28/2026

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 generates the...

Gadgets 360

Google DeepMind Introduces Genie 4 With Real-Time Simulation, Native Audio Generation

10/28/2026

Genie 4 allows users to modify a running simulation through natural-language prompts, as per Google.

Dataconomy

Google DeepMind previews Genie 4 world model

10/28/2026

Genie 4 maintains consistent scenes for up to two minutes, with improved physics and Gemini integration to explore robot tasks in simulation.

Digit

Google unveils Genie 4, an AI model that can create realistic virtual worlds with sound and physics

10/28/2026

Google has introduced Genie 4, a new AI model that can create realistic, interactive virtual worlds with sound, natural movements and real-world physics.