Skip to content
AI News HubLIVE
More
Summary only

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

Google DeepMind released Genie 4 as a research preview, a real-time world model that generates explorable worlds with native audio and live dialogue, while a Gemini 3.8 Flash planner runs inside the simulation loop.

SourceMarkTechPostAuthor: Michal Sutter
Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Genie 4 generates explorable visual worlds, ambient sound and character dialogue in real time, steerable via text prompts.
  • Gemini 3.8 Flash interprets, plans, verifies frames and replans inside the runtime loop, while Gemini Omni anchors each world's look and behavior.
  • No parameters, resolution, frame rate or benchmarks were disclosed; scene drift and short sessions remain key limitations.
  • Access starts with trusted testers, followed by Google AI Ultra subscribers and Gemini API partners.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models