OpenAI has released Sora 2, its most advanced video and audio generation model to date, delivering far more realistic, physically accurate, and controllable results compared to earlier systems.
Unlike prior video models that often distorted reality to fulfill a prompt, Sora 2 can handle complex physics, from Olympic-level gymnastics routines to dynamic backflips on paddleboards, while also generating synchronized dialogue and sound effects.
Alongside the model, OpenAI is launching a new iOS app called Sora, designed for social creativity.
The app introduces “cameos,” a feature that allows users to upload their likeness and voice to drop themselves into AI-generated scenes with striking realism.
Users can create, remix, and share generations, while OpenAI has built-in safety measures, including teen protections, consent controls, and a well-being-focused feed design.
Available first in the U.S. and Canada, Sora 2 marks a new step toward general-purpose simulation systems and world-scale creativity.
You may also want to check out some of our other recent updates.
Wanna know what’s trending online every day? Subscribe to Vavoza Insider to access the latest business and marketing insights, news, and trends daily with unmatched speed and conciseness! 🗞️
