OpenAI’s text-to-video generator tool, Sora, will soon be available to the general public. The ChatGPT maker first showcased the tool on February 15, 2024. However, at the time, OpenAI didn’t announce a public launch timeline for the product. Nonetheless, the company’s CTO, Mira Murati, has disclosed when the tool will be publicly available.
Mira Murati Confirms Sora Will Arrive This Year
In an interview with the Wall Street Journal, Murati states that OpenAI’s Sora will be available this year, possibly within a few months. Earlier today, we published a report on OpenAI’s accidentally pushed blog that revealed some details about the GPT-4.5 Turbo model. Since the expected launch timeline for this model is around August, we can expect OpenAI to release Sora after that.
OpenAI Also Wants To Add Sounds To Sora-Generated Videos
In addition to making Sora available to everyone, OpenAI plans to add audio capabilities to provide a wholesome experience. Previously, we’ve heard about ElevenLabs’ AI Sound Generator, which used Sora-generated videos to showcase its audio generation capabilities. There’s a good chance that OpenAI will implement a similar feature soon. In the long run, OpenAI wants to make Sora a versatile editing and creation tool.
In a public statement, OpenAI mentions that Sora deeply understands language, enabling it to interpret prompts accurately and generate compelling characters that express vibrant emotions. Further, when the tool arrives, it should also be able to take multiple shots within one video with a consistent subject and visual style. Murati also mentioned that Sora won’t generate the image of public figures on release. Last but not least, the company also mentioned that it is using publicly available or licensed data to train the text-to-video generator.
You can follow Smartprix on Twitter, Facebook, Instagram, and Google News. Visit smartprix.com for the most recent news, reviews, and tech guides.
