OpenAI's much-anticipated text-to-video generation tool, Sora, has been creating waves in the tech world ever since its announcement by CEO Sam Altman last month. The tool, which boasts groundbreaking capabilities, has captivated social media users with its ability to generate videos from text prompts.
Sam Altman's announcement of Sora came alongside an invitation to followers to submit prompts for the tool, resulting in a flurry of excitement surrounding the 60-second videos it produced. With its remarkable performance, Sora has emerged as a strong contender among video generation tools, potentially setting a new standard in the field.
Despite the buzz generated by Sora, it has yet to be made available to the general public. However, OpenAI's Chief Technology Officer, Mira Murati, hinted at an impending change during an interview with The Wall Street Journal. Murati provided insights into Sora's capabilities, emphasizing its ability to rapidly generate intuitive videos from simple text inputs.
Currently accessible only to select professionals such as visual artists, designers, and filmmakers, Sora's availability is set to expand in the near future. Murati confirmed that the tool will be released to the public "this year," indicating that eager users can expect access within a few months.
Excitingly, OpenAI has plans to enhance Sora further by incorporating audio into the generated videos, aiming to elevate the user experience with a realistic touch. Murati expressed the company's broader vision for Sora, envisioning it as a versatile tool for editing and content creation.
In terms of data utilization, Murati clarified that Sora's training data primarily consisted of publicly available or licensed content, leveraging images sourced from platforms like Shutterstock. Additionally, she underscored OpenAI's commitment to privacy and ethical usage, affirming that Sora will not generate videos featuring public figures and will watermark all outputs as a precautionary measure.
