{"id":185506,"date":"2025-10-02T17:08:10","date_gmt":"2025-10-02T17:08:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/au\/185506\/"},"modified":"2025-10-02T17:08:10","modified_gmt":"2025-10-02T17:08:10","slug":"openais-sora-2-lets-users-insert-themselves-into-ai-videos-with-sound","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/au\/185506\/","title":{"rendered":"OpenAI\u2019s Sora 2 lets users insert themselves into AI videos with sound"},"content":{"rendered":"<p>On Tuesday, OpenAI <a href=\"https:\/\/openai.com\/index\/sora-2\/\" rel=\"nofollow noopener\" target=\"_blank\">announced<\/a> Sora 2, its second-generation video-synthesis AI model that can now generate videos in various styles with synchronized dialogue and sound effects, which is a first for the company. OpenAI also launched a new iOS social app that allows users to insert themselves into AI-generated videos through what OpenAI calls &#8220;cameos.&#8221;<\/p>\n<p>OpenAI showcased the new model in an AI-generated video that features a photorealistic version of OpenAI CEO Sam Altman talking to the camera in a slightly unnatural-sounding voice amid fantastical backdrops, like a competitive ride-on duck race and a glowing mushroom garden.<\/p>\n<p>Regarding that voice, the new model can create what OpenAI calls &#8220;sophisticated background soundscapes, speech, and sound effects with a high degree of realism.&#8221; In May, Google&#8217;s <a href=\"https:\/\/arstechnica.com\/ai\/2025\/05\/ai-video-just-took-a-startling-leap-in-realism-are-we-doomed\/\" rel=\"nofollow noopener\" target=\"_blank\">Veo 3<\/a> became the first video-synthesis model from a major AI lab to generate synchronized audio as well as video. Just a few days ago, Alibaba released <a href=\"https:\/\/wan25.net\/\" rel=\"nofollow noopener\" target=\"_blank\">Wan 2.5<\/a>, an open-weights video model that can generate audio as well. Now OpenAI has joined the audio party with Sora 2.<\/p>\n<\/p>\n<p>\n      OpenAI demonstrates Sora 2&#8217;s capabilities in a launch video.<\/p>\n<p>The model also features notable visual consistency improvements over OpenAI&#8217;s previous video model, and it can also follow more complex instructions across multiple shots while maintaining coherency between them. The new model represents what OpenAI describes as its &#8220;GPT-3.5 moment for video,&#8221; comparing it to the ChatGPT breakthrough during the evolution of its text-generation models over time.<\/p>\n<p>Sora 2 appears to demonstrate improved physical accuracy over the original Sora model from <a href=\"https:\/\/arstechnica.com\/information-technology\/2024\/02\/openai-collapses-media-reality-with-sora-a-photorealistic-ai-video-generator\/\" rel=\"nofollow noopener\" target=\"_blank\">February 2024<\/a>, with OpenAI claiming the model can now simulate complex physical movements like Olympic gymnastics routines and triple axels while maintaining realistic physics. Last year, shortly after the launch of Sora 1 Turbo, <a href=\"https:\/\/arstechnica.com\/information-technology\/2024\/12\/twirling-body-horror-in-gymnastics-video-exposes-ais-flaws\/\" rel=\"nofollow noopener\" target=\"_blank\">we saw<\/a> several notable failures of similar video-generation tasks that OpenAI claims to have addressed with the new model.<\/p>\n<p>&#8220;Prior video models are overoptimistic\u2014they will morph objects and deform reality to successfully execute upon a text prompt,&#8221; OpenAI wrote in its announcement. &#8220;For example, if a basketball player misses a shot, the ball may spontaneously teleport to the hoop. In Sora 2, if a basketball player misses a shot, it will rebound off the backboard.&#8221;<\/p>\n","protected":false},"excerpt":{"rendered":"On Tuesday, OpenAI announced Sora 2, its second-generation video-synthesis AI model that can now generate videos in various&hellip;\n","protected":false},"author":2,"featured_media":185507,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[256,254,255,64,63,105],"class_list":{"0":"post-185506","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-au","12":"tag-australia","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/185506","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/comments?post=185506"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/posts\/185506\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media\/185507"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/media?parent=185506"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/categories?post=185506"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/au\/wp-json\/wp\/v2\/tags?post=185506"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}