Wire flash
Google DeepMind releases Genie 4 real-time interactive world model with native audio
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
Google DeepMind announced Genie 4, a new world model focused on real-time interactive simulation and improved photorealistic quality. According to the company, Genie 4 is the first real-time world model to natively generate audio, including ambient sound and real-time interactive character dialogue. Google DeepMind provided a full official explanation of Genie 4's real-time interaction, native audio, and collaboration mechanisms with Gemini. The company also acknowledged current limitations in long-horizon consistency and physical accuracy.
Source report
Google DeepMind has released Genie 4, a world model featuring real-time interactive simulation and enhanced photorealistic quality. For the first time in a real-time world model, it natively generates audio, including ambient sound and real-time interactive character dialogue.
The official documentation provides a complete account of Genie 4's real-time interaction, native audio, and its collaboration mechanism with Gemini. It also openly acknowledges current limitations in long-term consistency and physical accuracy.
Source
aihotNeutral / independent
Part of this Story
Google DeepMind Releases Genie 4 World Model With Native Audio and Real-Time Steering