{"id":5475,"date":"2024-03-14T09:17:51","date_gmt":"2024-03-14T01:17:51","guid":{"rendered":"https:\/\/www.1ai.net\/?p=5475"},"modified":"2024-03-14T09:17:51","modified_gmt":"2024-03-14T01:17:51","slug":"openai-%e9%a6%96%e5%b8%ad%e6%8a%80%e6%9c%af%e5%ae%98%ef%bc%9a%e6%96%87%e7%94%9f%e8%a7%86%e9%a2%91%e5%b7%a5%e5%85%b7-sora-%e6%95%b0%e6%9c%88%e5%86%85%e5%b0%86%e5%85%ac%e5%bc%80%e5%8f%91%e5%b8%83","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/5475.html","title":{"rendered":"OpenAI CTO: Sora, a video generation tool, will be released to the public in a few months and will support audio generation"},"content":{"rendered":"<p data-vmark=\"5478\">The Wall Street Journal published an interview on 13 (today) local time with the <a href=\"https:\/\/www.1ai.net\/en\/tag\/openai\" title=\"[View articles tagged with [OpenAI]]\" target=\"_blank\" >OpenAI<\/a> Interview with Mira Mulati, Chief Technology Officer. She stated.<a href=\"https:\/\/www.1ai.net\/en\/tag\/sora\" title=\"[See articles with [Sora] label]\" target=\"_blank\" >Sora<\/a> will be launched this year, \"probably in a couple months.\"<\/p>\n<p data-vmark=\"d982\">In addition to making Sora openly available to the public, OpenAI plans to add audio generation capabilities that may make the scenes more realistic, Mulati said. Also.<span class=\"accentTextColor\">The company also plans to allow users to edit Sora-generated content themselves<\/span>, \"because AI tools don't always generate accurate results\". She said the company is trying to find ways to enable users to edit and create audio and video content on their own.<\/p>\n<p data-vmark=\"0525\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-5476\" title=\"a2a510c8-9430-47f6-94a8-bbdc20727ec9\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/03\/a2a510c8-9430-47f6-94a8-bbdc20727ec9.jpg\" alt=\"a2a510c8-9430-47f6-94a8-bbdc20727ec9\" width=\"1440\" height=\"903\" \/><\/p>\n<p data-vmark=\"cd86\">When asked what data OpenAI used to train Sora, Murati didn't give a very specific answer: \"I'm not going to go into the details of the data used,\" he said.<span class=\"accentTextColor\">However, these data are publicly available or licensed data<\/span>.\" At the same time, she wasn't sure if videos from YouTube, Facebook, and Instagram were used, saying only that the content Sora used came from Shutterstock because of their partnership.<\/p>\n<p data-vmark=\"d1a7\">In addition, Murati said that Sora, after the release of<span class=\"accentTextColor\">\"Likely\" to not be able to generate audio\/video containing public figures<\/span>The videos will also come with AI watermarks.<\/p>\n<p data-vmark=\"10b3\">Three members of the Sora core team were recently on the WVFRM podcast, and they also said that Sora is still in the feedback phase, \"<span class=\"accentTextColor\">It is not a product yet and will not be available to the public anytime soon.<\/span>. &quot;<\/p>\n<p data-vmark=\"d953\">Not long ago, on March 10th, Pika, another text-to-speech video platform, announced a new feature that allows users to seamlessly generate and integrate sound into Pika-generated videos.<span class=\"accentTextColor\">You can describe the desired sound with a cue word, or just let Pika automatically generate the sound based on the video content.<\/span>.<\/p>","protected":false},"excerpt":{"rendered":"<p>The Wall Street Journal published an interview with OpenAI CTO Mira Mulati on 13 (today) local time. She said that Sora will be available this year, \"probably in a few months.\" In addition to making Sora openly available to the public, OpenAI plans to include audio generation features that may make scenarios more realistic, Mulati said. In addition, the company plans to allow users to edit the content generated by Sora themselves, \"because AI tools don't always produce accurate results.\" She said the company is trying to find ways to allow users to edit and create audio-visual content on their own. When asked what data OpenAI used to train Sora, Murati didn't give a very specific answer: 'I'm not going to go into details'<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[190,1249,1666],"collection":[],"class_list":["post-5475","post","type-post","status-publish","format-standard","hentry","category-news","tag-openai","tag-sora","tag-1666"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/5475","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=5475"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/5475\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=5475"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=5475"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=5475"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=5475"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}