Radar / AI media tools / Genie 4
Genie 4: Google's interactive world model, now in the Gemini API
DeepMind's world model streams continuous 720p interactive worlds at 24fps with native synchronized audio, now callable through the Gemini API.
Why it matters
The first world model developers can actually build with: a playable world generated live from a prompt or photo, steered by keyboard and mid-session text.
What you could build with it
An indie game studio could prototype playable game worlds from a text prompt in an afternoon, walking through the generated level with keyboard controls to test layout and mood before committing art budget to a single scene.
Does it hold up?
Too early to judge: the API opened 19 Nov, sessions cap at 120 seconds and cost ~$0.10/second, so real-world builds are still demo-scale.
Built with Genie 4
- Google opens Genie 4 world model to developers in Gemini APIarticle · Writeup of the API opening, the models/genie-4 identifier, WebRTC/WebSocket transport, and ~$0.10/second pricing.
- Genie 4 API: 720p worlds at 24 framesarticle · Independent review of the API release: 120-second session cap, no resume, and the real cost math at $6.05 a minute.
- Genie 4 API lets developers stream playable 720p worlds livearticle · Coverage of the 19 November API opening, 720p/24fps streaming with native audio, and the per-second billing model.
Learn more
First spotted on article: source.
More AI media tools
Hyperframes: write HTML, render video — HeyGen's open video engine for AI agentsOpen-source renderer from HeyGen that turns HTML, CSS and JavaScript into MP4 video, built so AI coding agents can…media · JEV 0.78LTX-2.5: Lightricks' open-weights video world model with soundA 22B open-weights audio-video foundation model that generates synchronized video and audio from text, image or video…media · JEV 0.76MiniMax-H3-Image: open image generation and editing at 16 MP in 6 stepsMiniMax's open-weight image model: text-to-image and editing unified in one 33.1B checkpoint, generating about…media · JEV 0.6FastFrames: Apple's open video models that generate frames in 36 msApple and Cornell's family of autoregressive video diffusion models that generate 480p frames at interactive latency…media · JEV 0.57HeyGen Avatar 6: an audio-driven avatar model with script-aware gesturesHeyGen's next-generation audio-driven personal avatar model — script-aware gestures, native 2K output, a personal…media · JEV 0.52Kling Image 4.0: native 8K images with 2,000 characters of clean textKuaishou's Kling Image 4.0 generates natively in 8K, renders up to 2,000 characters of legible text in one image, and…media · JEV 0.48
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.