{"id":36362,"date":"2025-05-28T19:32:02","date_gmt":"2025-05-28T11:32:02","guid":{"rendered":"https:\/\/www.1ai.net\/?p=36362"},"modified":"2025-05-28T19:36:17","modified_gmt":"2025-05-28T11:36:17","slug":"%e8%85%be%e8%ae%af%e5%bc%80%e6%ba%90%e6%b7%b7%e5%85%83%e8%af%ad%e9%9f%b3%e6%95%b0%e5%ad%97%e4%ba%ba%e6%a8%a1%e5%9e%8b%ef%bc%9a%e4%b8%80%e5%bc%a0%e5%9b%be%e4%b8%80%e6%ae%b5%e9%9f%b3%e9%a2%91%e5%b0%b1","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/36362.html","title":{"rendered":"Tencent open source hybrid voice digital human model: a picture of a piece of audio can make the figure speak and sing"},"content":{"rendered":"<p>May 28 News.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%85%be%e8%ae%af\" title=\"[View articles tagged with [Tencent]]\" target=\"_blank\" >Tencent<\/a>The hybrid public announced in a post today<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bc%80%e6%ba%90\" title=\"[View articles tagged with [open source]]\" target=\"_blank\" >Open Source<\/a>origin of the universe<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%af%ad%e9%9f%b3%e6%95%b0%e5%ad%97%e4%ba%ba%e6%a8%a1%e5%9e%8b\" title=\"[Sees articles with [Voice Digital Man Model] labels]\" target=\"_blank\" >Voice Digital Human Model<\/a>, with just a picture and a piece of audio, you can make the main character in the picture speak and sing naturally.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-36363\" title=\"df22054cj00swyyoa00b3d000ic007tp\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2025\/05\/df22054cj00swyyoa00b3d000ic007tp.jpg\" alt=\"df22054cj00swyyoa00b3d000ic007tp\" width=\"660\" height=\"281\" \/><\/p>\n<p>The released and open source voice digital human model HunyuanVideo-Avatar, jointly developed by Tencent hybrid video model (HunyuanVideo) and Tencent Music Tianqin Labs MuseV technology, support<strong>Head and shoulders, half and full body views<\/strong>,as well as<strong>Multi-style, multi-species &amp; two-player scenarios<\/strong>, which is geared towards video creators to provide highly consistent and dynamic video generation capabilities.<\/p>\n<p>Users can upload character images and audio, and the HunyuanVideo-Avatar model will automatically understand the images and audio, such as<strong>Emotions embedded in the character's environment, audio<\/strong>etc., allowing the characters in the picture to speak or sing naturally, generating videos that contain natural expressions, lip synchronization, and full-body movements.<\/p>\n<p>HunyuanVideo-Avatar is suitable for short video creation, e-commerce and advertising and other application scenarios. It can generate clips of characters speaking, dialoguing and acting in different scenes, quickly create product introduction videos or multi-person interactive advertisements, and reduce production costs.<\/p>\n<p>The single-subject capability of HunyuanVideo-Avatar has been open-sourced and launched on Tencent's official website. Users can experience it in \"Model Square - Hunyuan Raw Video - Digital Human - Speech-driven - HunyuanVideo-Avatar\", which supports uploading and downloading.<strong>Audio not exceeding 14 seconds<\/strong>Video generation will be performed, and other capabilities will be gradually brought online and open-sourced in the future.<\/p>\n<p data-vmark=\"7931\">1AI attaches the relevant links below:<\/p>\n<ul class=\"list-paddingleft-2\">\n<li>\n<p data-vmark=\"fd07\">Experience the portal:<span class=\"link-text-start-with-http\">https:\/\/hunyuan.tencent.com\/<\/span>\u00a0modelSquare \/ home \/ play?modelId=126<\/p>\n<\/li>\n<li>\n<p data-vmark=\"e0cf\">Project home page:<span class=\"link-text-start-with-http\">https:\/\/hunyuanvideo-avatar.github.io<\/span><\/p>\n<\/li>\n<li>\n<p data-vmark=\"a91b\">Github:<span class=\"link-text-start-with-http\">https:\/\/github.com\/Tencent-Hunyuan\/HunyuanVideo-Avatar<\/span><\/p>\n<\/li>\n<li>\n<p data-vmark=\"e120\">CNB:<span class=\"link-text-start-with-http\">https:\/\/cnb.cool\/tencent\/hunyuan\/HunyuanVideo-Avatar<\/span><\/p>\n<\/li>\n<li>\n<p data-vmark=\"0379\">Technical report:<span class=\"link-text-start-with-http\">https:\/\/arxiv.org\/<\/span>\u00a0pdf\/2505.20156<\/p>\n<\/li>\n<\/ul>","protected":false},"excerpt":{"rendered":"<p>May 28 news, tencent mixed yuan public number today announced open source mixed yuan voice digital human model, just a picture and a piece of audio, you can let the protagonist in the picture naturally speak, sing. The released and open source voice digital human model HunyuanVideo-Avatar, jointly developed by Tencent mixed yuan video model (HunyuanVideo) and Tencent Music Tianqin Labs MuseV technology, supports head and shoulders, half-body and full-body scenes, as well as multi-style, multi-species and two-person scenes, providing video creators with high consistency and dynamics. It provides video creators with highly consistent and dynamic video generation capabilities. Users can upload character images and audio, and the HunyuanVideo-Avatar model will automatically understand the images and audio, such as the character's environment,<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[219,323,6778],"collection":[],"class_list":["post-36362","post","type-post","status-publish","format-standard","hentry","category-news","tag-219","tag-323","tag-6778"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/36362","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=36362"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/36362\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=36362"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=36362"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=36362"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=36362"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}