AI Trends

Trending story

Genie 4 supports real-time environment editing during sessions

1 reports1 story updatesUpdated Nov 18 08:00

Understand this story

Story summary

The English summary is being updated. See the reporting timeline below.

Latest development · Report

Google DeepMind Launches Genie 4, Bringing Real-Time World Editing and Native Audio to Project Genie

Developments

1 confirmed developments

  1. English translation is being prepared.

    Source:Google DeepMind

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Nov 18

  1. Google DeepMindFirst-partySelected

    Google DeepMind Launches Genie 4, Bringing Real-Time World Editing and Native Audio to Project Genie

    Google DeepMind has launched Genie 4 in Project Genie, allowing users to modify environments in real time with text prompts as they explore and experience native audio that changes with the scene. Project Genie has also added an agent that can orchestrate multimodal models through natural language to create worlds, compose soundtracks, and publish them to the community gallery. Genie 3's exploration time per session has also been extended from 60 seconds to up to 3 minutes, with support for linking worlds and using 360-degree panoramic images as input.

Related stories

  1. Related storiesGoogle DeepMind releases the Gemini Robotics 2.5 model
  2. Related storiesAnthropic releases Claude Opus 5.5
  3. Related storiesMeta launches Muse Wonder and Muse Wonder Full models
  4. Related storiesGemini 4 Argon appears on the GCP quota page