TLDRocket
Sign in

Sora 2 System Card

OpenAI Blog Covered by 3 sources

OpenAI released Sora 2, a new video and audio generation model that improves on the original Sora with better physics accuracy, sharper visual quality, synchronized audio, and greater control over style. The model demonstrates capabilities previously difficult for video generators to achieve, including more realistic rendering and expanded creative options. These improvements enable users to generate videos with more precise physical behavior and coordinated sound alongside video content.

Why it matters

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.

Also covered by

Related stories

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads 60+ sources, removes duplicate coverage, and summarises the day in two minutes. Free, no spam, unsubscribe anytime.