Speechmatics - API for Voice AI Agents
Mini toolsStarchild 1
By Odyssey
Starchild-1 is a multimodal world model preview from Odyssey, released on 17-05-2026, designed to simulate both visuals and sounds in real time. Unlike visual-only world models, Starchild-1 autoregressively generates synchronized audio and video while responding to streaming user input. Odyssey says users can continuously provide text, speech, and action inputs, allowing the generated environment, conversations, ambient sound, and world dynamics to change interactively instead of following a fixed offline video trajectory. Its focus is real-time audio-video world simulation for future interactive systems in areas such as gaming, education, robotics, companionship, healthcare, and defense.
New
Multimodal
Gen 3
Overview
Starchild-1 is Odyssey’s real-time multimodal world model that generates synchronized audio and video while responding continuously to user input.
About Odyssey
Odyssey is a US AI research lab building general-purpose world models — AI systems that generate real-time, interactive simulations of arbitrary environments. Products include Odyssey-2 (general-purpose world model), Starchild-1 (multimodal world model), Agora-1 (multi-agent shared simulation), and PROWL (RL adversarial framework). Applications span gaming, robotics, defense, education, and film. API-accessible. Raised $27M+ from EQT, GV, NVIDIA, and Samsung Next.
Industry:
Artificial Intelligence
Location:
Menlo Park, CA, US
Tools using Starchild 1
No tools found for this model yet.
Last updated: May 20, 2026
