OpenAI has released Sora 2, a state-of-the-art video and audio generation model featuring improved physics simulation, synchronized audio, enhanced steerability, and broader stylistic range. The system card outlines capabilities, safety measures, and a phased rollout via sora.com, a new iOS app, and future API access.
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.
# Sora 2 System Card
Source: [https://openai.com/index/sora-2-system-card/](https://openai.com/index/sora-2-system-card/)
OpenAISora 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\. The model follows user direction with high fidelity, enabling the creation of videos that are both imaginative and grounded in real\-world dynamics\. Sora 2 expands the toolkit for storytelling and creative expression, while also serving as a step toward models that can more accurately simulate the complexity of the physical world\. Sora 2 will be available via sora\.com, in a new standalone iOS Sora app, and in the future it will be available via our API\.
Sora 2’s advanced capabilities require consideration of new potential risks, including nonconsensual use of likeness or misleading generations\. To address these, we worked with internal red teamers to identify new challenges and inform corresponding mitigations\. We’re taking an iterative approach to safety, focusing on areas where context is especially important or where risks are still emerging and are not fully understood\.
Our iterative deployment includes rolling out initial access to Sora 2 via limited invitations, restricting the use of image uploads that feature a photorealistic person and all video uploads, and placing stringent safeguards and moderation thresholds on content involving minors\. We’ll continue to learn from how people use Sora 2 and refine the system to balance safety while maximizing creative potential\. This system card describes the model’s capabilities, potential risks, and the safety measures OpenAI has developed for a safe deployment of Sora 2\.
OpenAI releases Sora System Card detailing safety mitigations and red teaming efforts for Sora, their text-to-video generation model capable of creating up to 1080p videos with 20-second duration. The document outlines pre-training filtering, external red teaming across nine countries testing 15,000+ generations, and safeguards against misuse of likeness and misleading content.
OpenAI has launched Sora, its video generation technology, to the public with safety measures including C2PA metadata, watermarks, and safeguards against abuse. The system has known limitations in physics and complex actions but represents a significant advancement in AI-powered video creation capabilities.
OpenAI announces comprehensive safety measures for Sora 2 and the Sora app, including provenance signals, C2PA metadata embedding, consent-based likeness controls through characters, and enhanced protections for teen users. The approach combines technical safeguards like content filtering with policy-based guardrails to prevent misuse of AI-generated video.
OpenAI announces safety-focused launch of Sora 2 and the Sora app with built-in protections including watermarking, C2PA metadata, consent-based likeness controls, teen safeguards, and multi-layered content filtering for harmful material and audio.