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

Google DeepMind released Genie 4 as a research preview. The real-time world model adds native audio, live dialogue and text steering, with Gemini 3.8 Flash planning events inside the simulation loop.

Key Features

• Real-time world model — Genie 4 operates as a real-time world model.
• Native audio — The model adds native audio capabilities.
• Live dialogue and text steering — Users can interact through live dialogue and text-based steering.
• Gemini 3.8 Flash integration — Gemini 3.8 Flash plans events inside the simulation loop.

Availability

Google DeepMind released Genie 4 as a research preview.

The post Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio appeared first on MarkTechPost.