In partnership with
What Sora 2 is
Hello {{first_name|Motivated and Miffed Community}},
OpenAI’s new flagship video-and-audio generation model. Compared to the first Sora, it’s more physically accurate (better “world physics”), more realistic, and far more controllable, including synchronized dialogue and sound effects. It’s the engine behind the new Sora iOS app
How do you like this new look for Motivated and Miffed?
What it can do (capabilities in plain English)
Follow complex direction across multi-shot clips while keeping characters, style, and scene state consistent. OpenAI
Model real-world physics noticeably better than prior systems (e.g., missed basketballs rebound instead of “teleporting” into the hoop). OpenAI
Generate audio with video (ambient sound, SFX, and speech guided by your prompt). OpenAI Help Center
Image-to-video & remix: animate a still image (non-real-person images) or branch from an existing post with clear remix labeling; “cameos” let users opt-in their own likeness via a one-time verification. OpenAI Help Center
Find your next winning ad creative in seconds with AI
Most AI tools promise you thousands of ads at the click of a button. But do you really need more ads—or just better ones?
Kojo helps you cut through the noise. We analyze your paid social data to uncover the ideas with the highest chance of success. Then, our AI predicts which concepts will perform best, so you don’t waste budget testing what won’t work.
Instead of drowning in endless variations, Kojo sends your best idea straight to a real human creator who makes it engaging, authentic, and ready to win on social. The entire process takes less than 20 seconds, giving you certainty before you spend and better performance without the waste.
Why gamble on guesswork or settle for AI spam when you can launch ads proven to work, made by people, and backed by data?
Official demo videos
Accessibility & rollout
Where: Sora iOS app (invite-based rollout), with web access at sora.com after invite; Android “later.”
Who: Initial rollout U.S. and Canada, with intent to expand quickly to more countries.
Tiers: Sora 2 (fast, everyday creation) and Sora 2 Pro (higher fidelity; initially for ChatGPT Pro/API users on web, coming to the app).
Cost: Launching free with “generous limits,” subject to compute constraints.
API: Planned; not yet live.
👋 That’s all!
Sora 2 feels like the moment AI video moves from neat demo to something you can actually direct. The rollout is invite-only for now, but the demos show real control, real sound, and real-world physics—plus watermarks and provenance baked in. We’ll keep watching as access widens; for now, the best view is still the official samples.