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.
Our video generation model, Sora, is now available to use at sora.com. Users can generate videos up to 1080p resolution, up to 20 sec long, and in widescreen, vertical or square aspect ratios. You can bring your own assets to extend, remix, and blend, or generate entirely new content from text.
# Sora is here
Source: [https://openai.com/index/sora-is-here/](https://openai.com/index/sora-is-here/)
The version of Sora we are deploying has many limitations\. It often generates unrealistic physics and struggles with complex actions over long durations\. Although Sora Turbo is much faster than the February preview, we’re still working to make the technology affordable for everyone\.
We’re introducing our video generation technology now to give society time to explore its possibilities and co\-develop norms and safeguards that ensure it’s used responsibly as the field advances\.
All Sora\-generated videos come with[C2PA\(opens in a new window\)](https://help.openai.com/en/articles/8912793-c2pa-in-dall-e-3)metadata, which will identify a video as coming from Sora to provide transparency, and can be used to verify origin\. While imperfect, we’ve added safeguards like visible watermarks by default, and built an internal search tool that uses technical attributes of generations[2](https://openai.com/index/sora-is-here/#citation-bottom-2)to help verify if content came from Sora\.
Today, we’re blocking particularly damaging forms of abuse, such as child sexual abuse materials and sexual deepfakes[3](https://openai.com/index/sora-is-here/#citation-bottom-3)\. Uploads of people will be limited at launch, but we intend to roll the feature out to more users as we refine our deepfake mitigations[4](https://openai.com/index/sora-is-here/#citation-bottom-4)\. You can read more about our approach to safety and monitoring in[the system card](https://openai.com/index/sora-system-card/)as well as details on our red teaming efforts[5](https://openai.com/index/sora-is-here/#citation-bottom-5)\.
We hope this early version of Sora will enable people everywhere to explore new forms of creativity, tell their stories, and push the boundaries of what’s possible with video storytelling\. We’re excited to see what the world will create with Sora\.
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 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 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.
OpenAI shares first impressions of Sora from visual artists, filmmakers, and creative directors who used the text-to-video model in their workflows, highlighting its ability to bring surreal and previously impossible ideas to life. Featured creators include shy kids, Paul Trillo, Nik Kleverov, and August Kamp.