# TestingCatalog — ICYMI: Google DeepMind previews Genie 4 with native audio

- Company: TestingCatalog (testingcatalog.com)
- Announced: 2026-10-28T18:13:04+00:00
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://www.testingcatalog.com/icymi-google-deepmind-previews-genie-4-with-native-audio/
- Record: https://forck.live/items/28897-icymi-google-deepmind-previews-genie-4-with-native-audio
- Subject: AI models / agents / unreleased features
- Models affected: Genie 4, Gemini Omni, Gemini 3.8 Flash, Gemini 4 Argon, Genie 3

Google DeepMind has previewed Genie 4, a real-time world model that builds photorealistic environments with fluid motion and generates ambient sound, music-like audio and spoken dialogue. DeepMind says Genie 4 models aerodynamics, collisions, natural human movement and reactions to surroundings, with steerable characters, and calls it the company's first real-time world model with native audio. Users navigate with keyboard controls and reshape a running scene through text, so a prompt can change weather, move the camera, or add a person or object without restarting. For multi-step scenarios, Gemini 3.8 Flash acts as a guiding agent that watches frames, divides a goal into steps, tracks progress, checks outcomes and replans when the world changes or a user intervenes. The research preview is rolling out to trusted testers in creative industries, journalism, education, gaming and engineering, with experiments covering film previsualization, simulations from archival 2D photos, and game concepts. DeepMind says generated video and audio carry SynthID watermarks, and warns that visual details and object permanence can drift during long sessions, repeated complex edits or navigation.

## Evidence

Verbatim from https://www.testingcatalog.com/icymi-google-deepmind-previews-genie-4-with-native-audio/:

> Google DeepMind has unveiled Genie 4, a real-time world model that creates photorealistic environments with fluid motion while generating ambient sound, music-like audio, and spoken dialogue. Gemini Omni grounds appearance and behavior in the real world, while other Gemini models help preserve coherence. DeepMind sees it as a foundation for training robots and agents and for new interactive experiences.
> 
> This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak. pic.twitter.com/6mmSUm9BBO
> 
> Users navigate with keyboard controls and reshape a running scene through text. A prompt can change weather, move the camera, or add a person or object without restarting. Gemini adapts each request to context, then monitors and steers the world between inputs.
> 
> DeepMind says Genie 4 models aerodynamics, collisions, natural human movement, and reactions to surroundings, with steerable characters. It is the company's first real-time world model with native audio, from wind and waves to dialogue that responds to instructions or events.

---

Record: https://forck.live/items/28897-icymi-google-deepmind-previews-genie-4-with-native-audio
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md