WASHINGTON (dpa-AFX) - ChatGPT creator OpenAI announced that it would launch the much-anticipated test-to-video generator tool Sora this year.
The tool, initially introduced by CEO Sam Altman in February, is capable of generating 60-second videos based on text prompts.
During an interview with The Wall Street Journal, CTO Mira Murati confirmed that the tool will be soon available for public use, which at present is only available for selected professionals such as graphic designers, filmmakers, and visual artists.
Murati also revealed that the company plans to incorporate audio, which would likely make the scenes even more realistic. She added, 'We're trying to figure out how to use this technology as a tool that people can edit and create with'.
When asked about the source of data used to train Sora, Murati commented, 'I'm not going to go into the details of the data that was used, but it was publicly available or licensed data.' But she confirmed that Sora uses content from OpenAI's partner Shutterstock, a stock photography company.
The CTO hinted that Sora is 'much more expensive' to power. However, she assured that the company is planning to make the tool 'available at similar costs' to DALL-E, the company's AI text-to-image model.
Additionally, Murati said that Sora would not generate videos featuring public figures and would watermark each video to ensure privacy and ethical usage.
Copyright(c) 2024 RTTNews.com. All Rights Reserved
Copyright RTT News/dpa-AFX
© 2024 AFX News
