Model WarsSeptember 30, 2025via OpenAI Blog
Sora 2 System Card
Why it matters
OpenAI's next-gen video model introduces capabilities (physics accuracy, synchronized audio, enhanced steerability) that redefine the competitive landscape for multimodal AI. This is a direct capability leap that will force competitors to recalibrate their roadmaps.
Key signals
- Sora 2 announced as 'state of the art' video and audio generation model
- New capabilities: improved physics accuracy, sharper realism, synchronized audio, enhanced steerability, expanded stylistic range
- Builds on foundation of original Sora
- Published via official OpenAI System Card (Sep 30, 2025)
- Multimodal video + audio generation capability
The hook
Sora 2 ships with synchronized audio, physics accuracy, and expanded stylistic control—raising the bar on multimodal generation.
Sora 2 is our new state of the art video and audio generation model. Building on the foundation of Sora, this new model introduces capabilities that have been difficult for prior video models to achieve– such as more accurate physics, sharper realism, synchronized audio, enhanced steerability, and an expanded stylistic range.
Relevance score:78/100