Google rolls out Genie 4 to eligible AI Ultra subscribers
Google began rolling out Genie 4 through Project Genie to eligible Google AI Ultra subscribers after an October research preview for trusted testers.
Google began rolling out Genie 4 through Project Genie on November 18, giving eligible Google AI Ultra subscribers their first access to the model.
Google had opened a research preview to trusted testers in October. Its November announcement directs Google AI Pro members to a waitlist. The announcement gives no country list, detailed Ultra eligibility rules or rollout completion date.
Google DeepMind says users can change the weather, add characters or redirect the camera with text prompts while exploring a world. The company says the model generates sound as the scene unfolds, including ambient sound and character dialogue.
Google says the update adds a Project Genie agent that takes conversational instructions and coordinates several Google models to create the initial visuals and background music. The company says users can bring Gemini into a session as they explore to get suggestions or have it trigger events. Google says users can explore and remix curated and community-built worlds in the new gallery and publish their own worlds there.
Google DeepMind specifies Genie 4’s output as real-time 720p video at up to 24 frames per second with synchronized audio. Google identifies camera latency, audio accuracy and keeping worlds consistent over time as limitations.
More news

OpenAI rolls out Live Dictation across all ChatGPT plans

Snowflake adds generally available TwelveLabs video AI to Cortex functions

Stretto deploys Amazon Nova voice agent for bankruptcy intake
