{"id":4583,"date":"2024-04-19T17:26:15","date_gmt":"2024-04-19T17:26:15","guid":{"rendered":"https:\/\/internationalpulse.net\/?p=4583"},"modified":"2024-04-19T17:26:15","modified_gmt":"2024-04-19T17:26:15","slug":"microsofts-vasa-1-ai-model-can-generate-deepfakes-using-a-single-photo-and-speech-audio-track","status":"publish","type":"post","link":"https:\/\/internationalpulse.net\/?p=4583","title":{"rendered":"Microsoft&#8217;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track"},"content":{"rendered":"<p><\/p>\n<div id=\"post-176944\">\n<p>\t<!-- .post-header --><\/p>\n<div class=\"post-content description cf entry-content content-spacious\">\n<p><img decoding=\"async\" src=\"https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19093233\/microsoft-vasa-1-ai-model-deepfake.jpg\" alt=\"Microsoft VASA-1 AI Model Deepfake\" width=\"1280\" height=\"1098\"\/><br \/>You\u2019ve seen Flawless TrueSync, now check out Microsoft\u2019s VASA-1 AI model, which can generate deepfakes using a single photo and a short speech audio track. The generated clips result in deepfakes with lip movements that are precisely synchronized with the audio, while also capturing a large spectrum of facial nuances and natural head motions.<\/p>\n<p><span id=\"more-176944\"\/><br \/><iframe title=\"VASA-1: Microsoft Strikes Again - STUNNING lifelike AI video and audio from a single photograph\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/EmXhhquX2zU?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><noscript><iframe title=\"VASA-1: Microsoft Strikes Again - STUNNING lifelike AI video and audio from a single photograph\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/EmXhhquX2zU?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/noscript><br \/>To achieve this level of liveliness in a deepfake, Microsoft needed to develop a new holistic facial dynamics and head movement generation model that works in a face latent space using videos. The current model supports online generation of 512\u00d7512 videos at up to 40 FPS with negligible starting latency, thus paving the way for real-time engagements with lifelike avatars that emulate human conversational behaviors. There\u2019s no word yet on if VASA-1 will be released to the public.<\/p>\n<div class=\"aawp\">\n<div class=\"aawp-product aawp-product--horizontal aawp-product--ribbon aawp-product--sale\" data-aawp-product-asin=\"B0C7HKS2RF\" data-aawp-product-id=\"116829\" data-aawp-tracking-id=\"tec02e-20\" data-aawp-product-title=\"Microsoft Xbox Series S 1TB SSD Console Carbon Black - Includes Xbox Wireless Controller - Up to 120 frames per second - 10GB RAM 1TB SSD - Experience high dynamic range - Xbox Velocity Architecture     [vide\">\n<p>    <span class=\"aawp-product__ribbon aawp-product__ribbon--sale\">Sale<\/span><\/p>\n<div class=\"aawp-product__thumb\">\n<p>            <img decoding=\"async\" class=\"aawp-product__image\" src=\"https:\/\/m.media-amazon.com\/images\/I\/41g-GMZSevL._SL160_.jpg\" alt=\"Microsoft Xbox Series S 1TB SSD Console Carbon Black - Includes Xbox Wireless Controller - Up to 120...\"\/><\/p><\/div>\n<div class=\"aawp-product__content\">\n<p>            Microsoft Xbox Series S 1TB SSD Console Carbon Black &#8211; Includes Xbox Wireless Controller &#8211; Up to 120&#8230;        <\/p>\n<div class=\"aawp-product__description\">\n<ul>\n<li>XBOX SERIES S 1TB: Go all digital and experience next-gen speed and performance. Double the fun with double the storage.<\/li>\n<li>FASTER LOAD TIMES: Make the most of every gaming minute with Quick Resume, lightning-fast load times, and gameplay of up to 120 FPS \u2013 all powered by&#8230;<\/li>\n<li>IN THE BOX: Xbox Series S 1TB console, one Xbox Wireless Controller, an ultra high-speed HDMI cable, power cable, and 2 AA batteries.<\/li>\n<\/ul><\/div>\n<\/p><\/div>\n<\/div>\n<\/div>\n<blockquote>\n<p>Our method exhibits the capability to handle photo and audio inputs that are out of the training distribution. For example, it can handle artistic photos, singing audios, and non-English speech. These types of data were not present in the training set,\u201d said the researchers.<\/p>\n<\/blockquote><\/div>\n<p><!-- .post-content --><\/p>\n<div class=\"author-box\">\n<div class=\"image\"><img alt=\"\" src=\"https:\/\/secure.gravatar.com\/avatar\/afb428e7fa743a3919f977c62f43c97a?s=82&amp;r=g\" srcset=\"https:\/\/secure.gravatar.com\/avatar\/afb428e7fa743a3919f977c62f43c97a?s=164&amp;r=g 2x\" class=\"avatar avatar-82 photo\" height=\"82\" width=\"82\" decoding=\"async\"\/><\/div>\n<div class=\"content\">\n<p>\t\t\t<span class=\"author\"><br \/>\n\t\t\t\t<span>Author<\/span><br \/>\n\t\t\t\tJackson Chung\t\t\t<\/span><\/p>\n<p class=\"text author-bio\">A technology, gadget and video game enthusiast that loves covering the latest industry news. Favorite trade show? Mobile World Congress in Barcelona.<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<div class=\"post-nav\">\n<div class=\"post previous cf\">\n<p>\t\t\t<i class=\"fa fa-angle-left\"\/><\/p>\n<p>\t\t<span class=\"content\"><\/p>\n<p>\t\t\t\t<img width=\"230\" height=\"230\" src=\"https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19084434\/razer-kishi-ultra-mobile-gaming-controller-230x230.jpg\" class=\"attachment-thumbnail size-thumbnail wp-post-image\" alt=\"Razer Kishi Ultra Mobile Gaming Controller\" decoding=\"async\" loading=\"lazy\" srcset=\"https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19084434\/razer-kishi-ultra-mobile-gaming-controller-230x230.jpg 230w, https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19084434\/razer-kishi-ultra-mobile-gaming-controller-370x370.jpg 370w, https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19084434\/razer-kishi-ultra-mobile-gaming-controller-150x150.jpg 150w\" sizes=\"(max-width: 230px) 100vw, 230px\"\/>\t\t\t<\/p>\n<p>\t\t<\/span>\n\t<\/div>\n<\/div>\n<\/div>\n<p> Microsoft&#8217;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track<br \/>\n<br \/>#Microsofts #VASA1 #Model #Generate #Deepfakes #Single #Photo #Speech #Audio #Track<\/p>\n","protected":false},"excerpt":{"rendered":"<p>You\u2019ve seen Flawless TrueSync, now check out Microsoft\u2019s VASA-1 AI model, which can generate deepfakes&#8230;<\/p>\n","protected":false},"author":1,"featured_media":4584,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[2732,2729,1039,2727,1678,2730,274,2731,1026,2728],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v19.10 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Microsoft&#039;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/internationalpulse.net\/?p=4583\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Microsoft&#039;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse\" \/>\n<meta property=\"og:description\" content=\"You\u2019ve seen Flawless TrueSync, now check out Microsoft\u2019s VASA-1 AI model, which can generate deepfakes...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/internationalpulse.net\/?p=4583\" \/>\n<meta property=\"og:site_name\" content=\"International Pulse\" \/>\n<meta property=\"article:published_time\" content=\"2024-04-19T17:26:15+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19093233\/microsoft-vasa-1-ai-model-deepfake.jpg\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/internationalpulse.net\/?p=4583\",\"url\":\"https:\/\/internationalpulse.net\/?p=4583\",\"name\":\"Microsoft's VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse\",\"isPartOf\":{\"@id\":\"https:\/\/internationalpulse.net\/#website\"},\"datePublished\":\"2024-04-19T17:26:15+00:00\",\"dateModified\":\"2024-04-19T17:26:15+00:00\",\"author\":{\"@id\":\"https:\/\/internationalpulse.net\/#\/schema\/person\/d507bf8682a9ef7e3ad7a69d9db5e1c3\"},\"breadcrumb\":{\"@id\":\"https:\/\/internationalpulse.net\/?p=4583#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/internationalpulse.net\/?p=4583\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/internationalpulse.net\/?p=4583#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/internationalpulse.net\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Microsoft&#8217;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/internationalpulse.net\/#website\",\"url\":\"https:\/\/internationalpulse.net\/\",\"name\":\"International Pulse\",\"description\":\"There&#039;s a different sound here\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/internationalpulse.net\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/internationalpulse.net\/#\/schema\/person\/d507bf8682a9ef7e3ad7a69d9db5e1c3\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/internationalpulse.net\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/f8e3f392738821708fe4235b6ffa7215?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/f8e3f392738821708fe4235b6ffa7215?s=96&d=mm&r=g\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/demo6.aiwalls.com\/automatic-news\"],\"url\":\"https:\/\/internationalpulse.net\/?author=1\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Microsoft's VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/internationalpulse.net\/?p=4583","og_locale":"en_US","og_type":"article","og_title":"Microsoft's VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse","og_description":"You\u2019ve seen Flawless TrueSync, now check out Microsoft\u2019s VASA-1 AI model, which can generate deepfakes...","og_url":"https:\/\/internationalpulse.net\/?p=4583","og_site_name":"International Pulse","article_published_time":"2024-04-19T17:26:15+00:00","og_image":[{"url":"https:\/\/images.techeblog.com\/wp-content\/uploads\/2024\/04\/19093233\/microsoft-vasa-1-ai-model-deepfake.jpg"}],"author":"admin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"admin","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/internationalpulse.net\/?p=4583","url":"https:\/\/internationalpulse.net\/?p=4583","name":"Microsoft's VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track - International Pulse","isPartOf":{"@id":"https:\/\/internationalpulse.net\/#website"},"datePublished":"2024-04-19T17:26:15+00:00","dateModified":"2024-04-19T17:26:15+00:00","author":{"@id":"https:\/\/internationalpulse.net\/#\/schema\/person\/d507bf8682a9ef7e3ad7a69d9db5e1c3"},"breadcrumb":{"@id":"https:\/\/internationalpulse.net\/?p=4583#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/internationalpulse.net\/?p=4583"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/internationalpulse.net\/?p=4583#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/internationalpulse.net\/"},{"@type":"ListItem","position":2,"name":"Microsoft&#8217;s VASA-1 AI Model Can Generate Deepfakes Using a Single Photo and Speech Audio Track"}]},{"@type":"WebSite","@id":"https:\/\/internationalpulse.net\/#website","url":"https:\/\/internationalpulse.net\/","name":"International Pulse","description":"There&#039;s a different sound here","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/internationalpulse.net\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/internationalpulse.net\/#\/schema\/person\/d507bf8682a9ef7e3ad7a69d9db5e1c3","name":"admin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/internationalpulse.net\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/f8e3f392738821708fe4235b6ffa7215?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/f8e3f392738821708fe4235b6ffa7215?s=96&d=mm&r=g","caption":"admin"},"sameAs":["http:\/\/demo6.aiwalls.com\/automatic-news"],"url":"https:\/\/internationalpulse.net\/?author=1"}]}},"featured_image_urls":{"full":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake.jpg",1280,1098,false],"thumbnail":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-150x150.jpg",150,150,true],"medium":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-300x257.jpg",300,257,true],"medium_large":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-768x659.jpg",640,549,true],"large":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-1024x878.jpg",640,549,true],"1536x1536":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake.jpg",1280,1098,false],"2048x2048":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake.jpg",1280,1098,false],"covernews-slider-full":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-1115x715.jpg",1115,715,true],"covernews-slider-center":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-800x500.jpg",800,500,true],"covernews-featured":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-1024x878.jpg",1024,878,true],"covernews-medium":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-540x340.jpg",540,340,true],"covernews-medium-square":["https:\/\/internationalpulse.net\/wp-content\/uploads\/2024\/04\/microsoft-vasa-1-ai-model-deepfake-400x250.jpg",400,250,true]},"author_info":{"display_name":"admin","author_link":"https:\/\/internationalpulse.net\/?author=1"},"category_info":"<a href=\"https:\/\/internationalpulse.net\/?cat=8\" rel=\"category\">main story<\/a>","tag_info":"main story","comment_count":"0","_links":{"self":[{"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/posts\/4583"}],"collection":[{"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4583"}],"version-history":[{"count":0,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/posts\/4583\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=\/wp\/v2\/media\/4584"}],"wp:attachment":[{"href":"https:\/\/internationalpulse.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4583"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4583"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/internationalpulse.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4583"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}