OpenAI has officially launched Sora, its highly anticipated text-to-video AI model, marking a significant milestone in AI-driven creative tools. Released as part of OpenAI’s “ship-mas” event, Sora promises to revolutionize how users generate video content. Available now for ChatGPT subscribers in the US and most other countries, it allows users to create dynamic, AI-generated videos directly from text prompts.

For those subscribed to ChatGPT Plus ($20/month), you can generate up to 50 priority videos at 720p resolution and 5-second durations, along with new features that include image animations and video remixing. The premium ChatGPT Pro subscription ($200/month) offers even more, with up to 500 priority videos, 1080p resolution, 20-second durations, and the option to download videos without watermarks.

Sora Turbo, an updated and faster version of the model, was also announced alongside the original. This variant provides new options like multiple aspect ratios (widescreen, vertical, square), longer video durations, and faster video processing. Users can remix videos, blend scenes, and generate videos from text, images, or videos, making it highly flexible.

One of the most exciting features introduced is the storyboard tool, which allows users to create detailed sequences for video production. OpenAI also showcased Sora’s ability to animate photos and remix existing footage with the new AI “blending” tool.

However, OpenAI has implemented strong safety measures for content moderation. Videos generated through Sora will display a watermark and metadata indicating AI generation. Users are required to agree that their uploads do not contain inappropriate or copyrighted material.

While the release has been met with overwhelming demand, OpenAI has acknowledged that it may take some time for everyone to gain access, given the high interest in the tool. So, while Sora is available now for many users, it might still take a while for full availability across all regions.