From clip-makers to simulators: Odyssey's new world models
About this episode
The episode discusses Odyssey's new world models, Starchild-1 and Agora-1, and their technical innovations.
Odyssey just shipped two new world models. Starchild-1 generates synchronized audio and video in real time at up to 24 fps, responding to streaming text, speech, or action input - the first real-time multimodal world model. Agora-1 puts up to four players into a shared simulated deathmatch on GoldenEye, with every frame each player sees generated on the fly while the model holds a shared world state across all participants. We walk through both releases, the technical contributions behind them - a causal distillation pipeline from a bidirectional audio-video foundation model, an asynchronous KV-cache that handles the audio/video clock mismatch, and a decoupled simulation/rendering architecture for the multi-agent case - and why world models are a different shape of system than the clip-makers (Veo, Sora, Kling) that have dominated generative video for three years. Odyssey is an Air Street Capital portfolio company. Jeff Hawke, Odyssey's co-founder and CTO, presents this work at RAAIS 2026 in London on June 12.
More episodes of Air Street Press
- Speech-to-text at conversation speed - Angelos Perivolaropoulos, ElevenLabs
- What it takes to ship AI under regulation - Nikolay Donets, Revolut
- The next gene editor will be designed: Profluent + Lilly, $2.25B
- State of AI Report: 2026 newsletter
- From catastrophic forgetting to frontier AI - Raia Hadsell, Google DeepMind
- When agents need to keep learning - Roberta Raileanu, Google DeepMind
Explore listener stats, chart rankings, contacts and more on the Air Street Press podcast page.