Video & Creative AI
Google Genie 4 adds audio and real-time editing
The Verge AIhigh confidence
Why it matters
- →Real-time natural language editing allows users to modify generated scenes dynamically rather than regenerating from scratch.
- →Synchronized audio generation adds a critical layer of realism to interactive world simulations.
- →Extended two-minute duration improves coherence for longer-form pre-visualization tasks compared to previous iterations.
Google announced Genie 4, an updated world model for generating interactive AI experiences. The new version incorporates Gemini 3.8 Flash to enable real-time natural language editing and audio generation, extending output duration from one to two minutes. While designed for prototyping in gaming and film, the model exhibits degradation in object permanence during longer simulations. Access is currently limited to a research preview for trusted testers and Google AI Ultra subscribers.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Google DeepMind Launches Nano Banana 2 Lite and Gemini Omni Flash
Google DeepMind · June 30, 2026 · Background
- 2Gemini Omni Flash API Released for Video Editing
Sam Witteveen · June 30, 2026 · Background
- 3Google Photos introduces AI 'Video Remix' tool
TechCrunch AI · July 8, 2026 · Background
- 4Google Vids Enhances Video Creation with AI Tools
Google AI Blog · July 16, 2026 · Background
- 5Google DeepMind Launches Gemini Omni 1.1 Flash
Google DeepMind · August 27, 2026 · Related
- 6Google Releases Gemini 3.8 Flash Model
Matthew Berman · September 3, 2026 · Background
- 7Adobe Enhances AI Tools in Premiere for Seamless Editing
The Verge AI · September 8, 2026 · Related
- 8Google Gemini 3.8 Flash TTS with Voice Cloning
Sam Witteveen · September 24, 2026 · Background
What happened next
- 9llama.cpp adds /v1/realtime API for live voice
llama.cpp Releases · October 28, 2026 · Background
Follow this story
Open the full story →Google Genie 4 adds audio and real-time editing
5 developments
- Oct 27 · The Verge AI
Google Genie 4 adds audio and real-time editing (This article) - Oct 27 · TechCrunch AI
Google Genie 4 adds audio and real-time steering - Oct 28 · The Rundown AI
Genie 4 adds sound and interactive characters - Oct 29 · The AI Daily Brief
Google Genie 4 Enables Real-Time Playable World Creation - Oct 30 · Matt Wolfe
DeepMind Genie 4 Creates Real-Time AI Worlds
More from The Verge AI
© The Verge AICoding Toolscoding
DIY Muse Gadget proves Meta's hardware is just a dev kit
Meta’s Muse Charm isn’t a finished product; it’s an invitation to hack. A non-coder used Claude Code to transform a $50 Waveshare ESP32-S3 dev board into a fully functional AI companion, adding ElevenLabs voice synthesis, custom Tamagotchi-style minigames, and remote camera controls that Meta’s official firmware lacks. This reveals a critical truth: the value of Meta’s new hardware ecosystem lies not in its out-of-the-box utility, but in its open-source API allowing anyone to rewrite the experience. The gap between Meta’s polished demo and the actual user reality is bridged entirely by third-party AI coding tools.
The Verge AI
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© The Verge AIMarket & Regulationbusiness
Altman argues cloud RAM over local inference
Sam Altman is pushing back against the local AI trend, arguing that hoarding DRAM in personal devices is a global waste during a severe supply crunch. He points out that consumer hardware sits idle most of the time, whereas cloud data centers achieve the high utilization rates needed to justify the billions invested by players like OpenAI and Stargate. This isn't just an opinion; it's a defense of the centralized infrastructure model against the growing open-source movement. The real-world impact is visible in the locked-up supply from Samsung and SK Hynix, which drives up costs for everyone else.
The Verge AI
More in Video & Creative AI
© TechCrunch AIVideo & Creative AIimage
Meta launches AI fashion app Style Sketch
Meta is testing Style Sketch, an app that builds a virtual closet from Instagram photos and suggests outfits using generative AI. It’s not a breakthrough in technology—digitizing wardrobes and visualizing clothes is already done by startups like Alta—but the integration with Instagram’s massive user graph gives Meta a data advantage no competitor can easily replicate. The app also factors in weather and itinerary for trip planning, turning static image generation into contextual lifestyle assistance. This launch signals Meta’s strategy to leverage AI efficiency to ship niche consumer apps rapidly, even if they don't reinvent the wheel.
TechCrunch AI
© WIRED AIVideo & Creative AIother
Entravision's AI Co-host Coyotec Drives Ratings Surge
Entravision’s Coyotec proves AI can drive real audience growth in traditional media. By combining Claude Haiku for logic and Eleven Labs for voice, the station achieved an 84.9% listener increase among young Hispanics. This isn't just a tech demo; it's a commercial win that challenges the 'human-only' stance of competitors like iHeartRadio.
WIRED AI
© TechCrunch AIVideo & Creative AIvideo
Grok releases first seven minutes of AI Odyssey
Grok’s seven-minute 'Odyssey' clip proves generative video has crossed from novelty into narrative capability, with coherent scenes and realistic water that trick the eye. The production, a collaboration with Wonder Studios, shows technical competence in character consistency and environment rendering, yet it remains emotionally hollow and visually airless. This release signals that AI can now handle long-form storytelling structures, even if the artistic soul is still missing. It shifts the conversation from 'can AI make a video?' to 'can AI make a compelling one?'
TechCrunch AI