Get ready to experience OpenAI’s groundbreaking text-to-video generator, Sora, for yourself. In an interview with The Wall Street Journal, OpenAI’s chief technology officer, Mira Murati, revealed that Sora will be available to the public “this year,” potentially within the next few months.
Sora, first unveiled by OpenAI in February, has the remarkable capability of generating hyperrealistic scenes based on text prompts. While initially available only to visual artists, designers, and filmmakers, some Sora-generated videos have already found their way onto platforms like X.
Murati shared that OpenAI plans to “eventually” incorporate audio into Sora, further enhancing the realism of the generated scenes. Additionally, the company aims to provide users with the ability to edit the content in the videos produced by Sora, as AI tools don’t always create accurate images. “We’re trying to figure out how to use this technology as a tool that people can edit and create with,” Murati told the Journal.
When questioned about the data used to train Sora, Murati remained vague, stating, “I’m not going to go into the details of the data that was used, but it was publicly available or licensed data.” She confirmed that Sora utilizes content from Shutterstock, with which OpenAI has a partnership, but was unsure if it used videos from YouTube, Facebook, and Instagram.
Murati acknowledged that Sora is “much more expensive” to operate compared to other AI models, but OpenAI is working to make the tool available at similar costs to DALL-E, their AI text-to-image model, when it launches for the public.
As the 2024 presidential election approaches, concerns regarding generative AI tools and their potential for misinformation have heightened. Murati stated that, similar to DALL-E’s policies, Sora likely won’t be able to produce images of public figures upon its release. Additionally, videos generated by Sora will feature a watermark to distinguish them from real footage, although watermarks aren’t a perfect solution.
The Wall Street Journal’s report showcases examples of Sora’s capabilities, including an animated bull in a China shop and a mermaid smartphone reviewer, highlighting the potential of this innovative technology.
