Theverge Google DeepMind Launches Genie 4 with Real-Time Audio and Enhanced Interactivity
Article Content
- •Genie 4 introduces real-time audio and dialogue in interactive simulations.
- •The model can maintain scene consistency for up to two minutes, improving user experience.
- •Currently in research preview, Genie 4 is aimed at gaming, robotics, and creative industries.
On October 27, 2026, Google DeepMind announced the release of Genie 4, a new world model that generates interactive environments with real-time audio and character dialogue. This model builds on its predecessor, Genie 3, by allowing users to modify scenes dynamically using natural language prompts. Genie 4 incorporates the Gemini 3.8 Flash model to maintain coherence in simulations, adapting to user inputs like weather changes or object additions. The model can sustain a consistent simulation for up to two minutes, double the previous limit. While Genie 4 is currently available only to select testers, it is being touted for applications in gaming, robotics, and creative fields such as film prototyping. However, the model is still experimental, with limitations in longer sessions where visual details may shift. Google aims to leverage Genie 4 to advance artificial general intelligence (AGI) by creating safe, variable simulations for training and creative ideation.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (10)
Following this threat?
Track Google DeepMind in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Common questions
What are the main features of Genie 4?
Who can access Genie 4 currently?
What industries could benefit from Genie 4?
Continue Reading
CVE-2026-121392 in FreeRDP Exposes RDP Sessions to Interception A vulnerability, CVE-2026-121392, has been identified in FreeRDP versions prior to 3.32.2, which allows man-in-the-middle attackers to bypass server identity checks. The flaw arises from improper certificate validation in the tls_verify_certificate() function, permitting attackers with a trusted certificate to…