Google DeepMind introduces Genie 4 real-time world model
Original title: Meet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio
The title says Genie 4 includes native audio, but the captured page is only a cookie notice.
A MarkTechPost item is headlined as an introduction to Google DeepMind’s Genie 4, described as a real-time world model with native audio. The text supplied with the item is a website cookie-consent banner and does not describe architecture, availability, benchmarks, or access. No further product facts can be taken from the page content.
Unconfirmed: Model capabilities beyond the title are unconfirmed because the article body was not included.
- The title attributes Genie 4 to Google DeepMind.
- Native audio and real-time operation are stated only in the title.
- The body text lists cookie names and durations, not model details.
- Organizations
- Google DeepMind
- AI models
- Genie 4
From the original article
14 min read at marktechpost.comGoogle 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.
By Michal Sutter · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.