- OpenAI’s sensational text-to-video converter will soon be available to everyone. OpenAI’s Mira Murati said in an interview with The Wall Street Journal that Sora will be available “this year” and “may take a few months.”
- OpenAI first demonstrated Sora in February, which can produce hyper-realistic scenes based on a text command. The company initially made the tool available only to visual artists, designers, and filmmakers, but that hasn’t stopped some Sora-created videos from appearing on platforms like X.
- The company also wants to allow users to edit the content in videos produced by Sora, since AI tools do not always produce accurate images.
OpenAI’s sensational text-to-video converter will soon be available to everyone. OpenAI chief technology officer Mira Murati said in an interview with The Wall Street Journal that Sora will be available “this year” and “may take a few months.”
OpenAI first demonstrated Sora in February, which can produce hyper-realistic scenes based on a text command. The company initially made the tool available only to visual artists, designers, and filmmakers, but that hasn’t stopped some Sora-created videos from appearing on platforms like X.
In addition to making the tool public, Murati says OpenAI plans to “eventually” include audio, which has the potential to make scenes even more realistic. The company also wants to allow users to edit the content in videos produced by Sora, since AI tools do not always produce accurate images. “We’re trying to figure out how to use this technology as a tool that people can edit and create,” Murati told the Journal. said.
When asked what data OpenAI used to train Sora, Murati wasn’t very specific and appeared to dodge the question. “I won’t go into details of the data used, but it was publicly available or licensed data.” says. Murati also says he’s not sure if videos from YouTube, Facebook and Instagram were used. He confirmed to the Journal only that Sora uses content from Shutterstock, which OpenAI partners with.
Murati also told the Journal that running Sora was “much more expensive.” When OpenAI makes the tool public, it is trying to make it available at “similar costs” as the company’s AI text-to-image model, DALL-E.
Compiled by: Alp Eren Gümüş
