The Einstein agent demonstrates how voice AI can unlock more interactive, accessible and multilingual education experiences. Try it here:
MULTIMODAL AI
-
Odyssey Launches Starchild-1 for Real-Time Generative World Models
By
–
World models just leveled up.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 19 mai 2026
Odyssey's Starchild-1 is the first AI that generates synchronized audio AND video in real-time — while responding to your inputs as it runs.
Not a clip. Not a render. A living, interactive world.
This is what general world intelligence looks like… pic.twitter.com/qitkjOBPJlWorld models just leveled up. Odyssey's Starchild-1 is the first AI that generates synchronized audio AND video in real-time — while responding to your inputs as it runs. Not a clip. Not a render. A living, interactive world. This is what general world intelligence looks like
-
Top AI Stories: OpenAI Lawsuit, Cursor 2.5, Claude 3D, World Models
By
–
Top stories in AI today: – Elon Musk loses lawsuit against OpenAI, Microsoft
– Cursor’s Composer 2.5 nears coding frontier
– 3D model anything with Claude and Blender
– Odyssey’s multimodal, multiplayer world models
– 4 new AI tools, community workflows, and more -
Human-like behavior is the next leap for AI avatars
By
–
La mayoría de avatares IA todavía parecen “texto con cara”.
— Nico (@nicos_ai) 19 mai 2026
Esto ya empieza a sentirse más como dirección creativa real.
Pausas, miradas, microexpresiones, gestos…
el salto no está en verse humano,
está en comportarse humano. https://t.co/Usw6RALizzMost AI avatars still look like "text with a face." This is already starting to feel more like real creative direction. Pauses, glances, microexpressions, gestures… the leap isn't in looking human,
it's in behaving human. -
Google I/O: AI-generated videos using Gemini Omni model
By
–
GOOGLE I/O 🔥: These legends are AI-generated via an upcoming Gemini Omni model.
— 🚨 AI News | TestingCatalog (@testingcatalog) 19 mai 2026
> Both videos are 8s HD samples.
> Video with Sandar and Demis is likely generated as an image-to-video using Omni for style editing.
> Logan's video is likely a "Likeness" Avatar and Omni video.… https://t.co/vRoP7yaFTk pic.twitter.com/sgX72LjAG3GOOGLE I/O : These legends are AI-generated via an upcoming Gemini Omni model. > Both videos are 8s HD samples.
> with Sandar and Demis is likely generated as an image-to-video using Omni for style editing.
> Logan's video is likely a "Likeness" Avatar and Omni video. -
HeyGen introduces granular gesture and expression control for AI avatars
By
–
Body language was the missing piece in avatar videos and HeyGen just handed it over.
— AI Highlight (@AIHighlight) 18 mai 2026
Type the gesture, type the expression, type the gaze.
The delivery finally matches https://t.co/qUsQCKZlVQBody language was the missing piece in avatar videos and HeyGen just handed it over. Type the gesture, type the expression, type the gaze. The delivery finally matches
-
Gemini Live Implementation Found in Desktop Client
By
–
That's the official (unreleased) implementation of Gemini Live inside the Gemini desktop. However, there is no guarantee that it won't change before it is released.
-
Runway video agents now support tool calling capabilities
By
–
Runway Characters can now take actions, not just speak. Tell the real-time video agent what you want, and they can call tools for you.
— Runway (@runwayml) 18 mai 2026
Learn more about how to integrate tool calling into your product at the link below. pic.twitter.com/PTqdUXUC7sRunway Characters can now take actions, not just speak. Tell the real-time video agent what you want, and they can call tools for you. Learn more about how to integrate tool calling into your product at the link below.
-
Unified Vision World Models framework from Beijing Jiaotong, ByteDance, Tencent
By
–
What if AI could learn the world just by watching? Researchers from Beijing Jiaotong, ByteDance, Tencent present a unified framework for Vision World Models: encoding visuals, learning dynamics, simulating outcomes. This survey outperforms fragmented taxonomies, outlining
-
Standardizing Skills for Portable AI Coding Agent Workflows
By
–
If you're building AI workflows for yourself or clients, the practical takeaway is simple: Write your Skills in the SKILL .md format. You're not locked to one vendor. Your thinking systems become portable across every major coding agent. One Skill, 30+ compatible tools. That's