Google DeepMind announced Genie 4, a real-time interactive world model that generates visuals, ambient sound, music and dialogue together and accepts natural-language steering while a Gemini-based agent helps maintain continuity. The research preview is rolling out to trusted testers, with a waitlist for future Project Genie, Gemini API and AI Studio access.
Why it matters: A steerable audiovisual simulator could become useful for agent and robotics training or interactive prototyping. Today the evidence is a vendor preview, not a broadly testable API, and known consistency limits constrain consequential simulation claims.
Meta launched Muse Image in Meta AI, meta.ai and selected messaging and Stories surfaces. Instead of relying on one diffusion pass, the system can search for references, write code for precise layouts and repeatedly inspect and refine its output. Meta also previewed Muse Video, a text-to-video model designed to generate synchronized audio natively.
Why it matters: Image generation is shifting from a single model call toward a composed workflow that can retrieve evidence, calculate layouts and critique its own drafts.
Google introduced Veo 3 with native audio generation, Imagen 4 with stronger image detail and typography, and Flow as an AI filmmaking workspace for prompts, ingredients, shots, and scene continuity.
Why it matters: Generative media moved from isolated clips to a workflow with assets, camera controls, continuity, and sound—closer to production previsualization.