Odyssey launches Starchild-1, a real-time multimodal AI world model with synchronized audio-video generation
Starchild-1 is the first real-time multimodal world model that generates synchronized audio + video while responding live to user input. Built for interactive AI, gaming, robotics, education, and…
Read the full articleYou might also wanna read
Odyssey Releases Agora-1: A Multi-Agent World Model for Shared Simulations
Agora-1, a multi-agent world model, enables multiple participants—human or AI—to share and interact within the same world simulation in real
odyssey.ml·1mo ago
Overworld Releases Waypoint-1: Real-Time Interactive Video Diffusion Model
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Google Gemini Omni: Multimodal AI That Processes Video, Audio, Images, and Text Simultaneously
Create anything from anything from any input – starting with video
deepmind.google·1mo ago
Kinetix Unveils Kamo-1: A 3D-Conditioned AI Video Generation Model with Physical Grounding
Research Lab Pioneering Frontier 3D & Human Motion Intelligence.
kinetix.tech·25d ago
Sparrow-1: AI Model for Human-Like Conversational Timing in Real-Time Voice Systems
Sparrow-1 is a specialized, multilingual audio model for real-time conversational flow and floor transfer. It predicts when a system should
tavus.io·6mo ago
Helios: A 14B Parameter Real-Time Video Generation Model for Minute-Scale Content
View recent discussion. Abstract: We introduce Helios, the first 14B video generation model that runs at 19.5 FPS on a single NVIDIA H100 GP
alphaxiv.org·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.