Google Makes Genie 4 Accessible Through Its Gemini API

Genie 4, launched yesterday, is now accessible to developers through the Gemini API, via the Interactions API, as well as in Google AI Studio. The model allows for experimentation with continuous worlds generated in 720p at 24fps.
Proposed Uses and Output Watermarking
All outputs carry an imperceptible SynthID watermark. Among the proposed uses are prototyping interactive experiences, visualizing spatial projects, and training robots and AI agents.
For initial trials, Google AI Studio provides an interactive canvas as well as starter applications. Information on pricing and documentation for the Gemini API is also available.
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisissez votre rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
Developers Modify Worlds in Real Time
Creating an environment can start from a written prompt, a reference image, or a combination of both. The sound, produced natively and synchronized, includes ambient sounds, sound effects, and character dialogues.
Keyboard commands, combined with live text instructions, are used to navigate these worlds. During navigation, it is possible to change weather conditions, lighting, objects, or events. Gemini's reasoning ensures the consistency of the environment's state throughout the experience.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.