GoKawiilGoogle DeepMind Debuts Genie 4 World Model With Audio and Longer Scenes
Google DeepMind released Genie 4 in research preview, a world model that generates photorealistic, interactive environments with real-time audio including music, ambient sound, and dialogue. The new model allows mid-simulation prompt edits like changing weather or camera angle, maintains consistent scenes for up to two minutes, and offers improved physics and more lifelike characters compared to last year's Genie 3. It's currently available to select testers, with broader access planned for Google AI Ultra subscribers.
GoKawiil's interpretation of the reporting above, not reported fact.
The addition of audio and longer, editable scenes suggests Google is pushing world models closer to practical simulation tools rather than short demos, which could matter for training other AI systems or content creation. Research director Tejas Kulkarni's comment about pairing Gemini with Genie hints at a future where text-generating models and world-simulating models work together, though how that combination will be used commercially remains unclear. Limiting early access to testers and paid subscribers also signals Google may be testing demand before a wider release.
- Genie 4 adds real-time audio and can hold a consistent scene for up to two minutes, double Genie 3's limit.
- Users can edit simulations mid-stream, altering weather, camera angles, or adding objects and people.
- Access is currently limited to select testers, with a broader rollout planned for Google AI Ultra subscribers.
Source: tech.slashdot.org, 2026-10-27
Published there as: “Google's Genie 4 World Model Adds Audio, More Realistic Worlds”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.