You will soon be able to try out the text-to-video generator. Mira Murati said in an interview with The Wall Street Journal that Sora will be available this year and that it could be a few months.
In February, Openai showed off Sora, which is capable of generating realistic scenes. The company only made the tool available for visual artists, designers, and filmmakers to start, but that didn't stop some Sora-generated videos from making their way onto platforms like X. The tool is being made available to the public, and Openai has plans to eventually incorporate audio, which could make the scenes even more realistic. The company wants to allow users to modify the content of the videos they produce. When asked what the data OpenAI used to train Sora was, Murati didn't get too specific. She wouldn't say what data was used, but she did say that it was publicly available or licensed. Sora is more expensive to power, according to Murati. When DALL-E is released to the public, Openai wants the tool to be available at similar costs. There are more examples of what kinds of videos this tool can produce in the Journal's report, including an animated bull in a China shop.