# Google opens Genie 4 research preview with live audio and scene editing

_Published Tuesday, October 27, 2026 at 3:18 PM EDT · AI · Latest · Tier 2 — Notable_

![Google opens Genie 4 research preview with live audio and scene editing — Primary](https://techcrunch.com/wp-content/uploads/2026/10/Genie-4-blog-header.png?resize=1200,675)

Google DeepMind released Genie 4 to trusted testers in a research preview, TechCrunch reported. The model generates interactive worlds with real-time audio and lets users change scenes through prompts during a simulation, including adding objects or changing the weather.

Genie 4 can maintain a consistent scene for up to two minutes, double its predecessor's limit. Google plans access for AI Ultra subscribers through Project Genie and early access partners of the Gemini API and Google AI Studio in the coming weeks. Objects and details can still drift during simulations, and the team acknowledged unresolved problems with audio accuracy and legible text inside generated worlds.

## Sources

- [TechCrunch](https://techcrunch.com/2026/10/27/googles-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering/)

---
Canonical: https://techandbusiness.org/newswire/mv5Yuk4VshDuGT-dC5nv9s
Published: 2026-10-27T19:18:48.590Z
Story chronology: 2026-10-27T16:30:57.000Z
Retrieved: 2026-10-27T22:10:17.199Z
Publisher: Tech & Business (techandbusiness.org)