{"id":53296,"date":"2026-05-23T12:42:27","date_gmt":"2026-05-23T04:42:27","guid":{"rendered":"https:\/\/www.1ai.net\/?p=53296"},"modified":"2026-05-23T12:42:27","modified_gmt":"2026-05-23T04:42:27","slug":"%e7%bd%91%e6%98%93%e6%9c%89%e9%81%93%e5%ad%90%e6%9b%b0-4%e5%a4%9a%e6%a8%a1%e6%80%81%e6%a8%a1%e5%9e%8b%e3%80%81%e8%af%ad%e9%9f%b3%e5%90%88%e6%88%90%e6%a8%a1%e5%9e%8b%e5%85%a8%e9%87%8f","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/53296.html","title":{"rendered":"Web-accessible \"sub\" multimodular models, speech synthesis models, full open source"},"content":{"rendered":"<div class=\"article-header\"><\/div>\n<div>\n<p>May 23rd.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e7%bd%91%e6%98%93\" title=\"[Sees articles with [Wepwire] labels]\" target=\"_blank\" >NetEase<\/a>Yesterday, it was announced that it was decided that the \"sub\" large model 4.0 core two engines --\"<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%9a%e6%a8%a1%e6%80%81%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [multimodal model]]\" target=\"_blank\" >Multimodal Model<\/a>\"and\"<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%af%ad%e9%9f%b3%e5%90%88%e6%88%90\" title=\"[Sees articles with [speech] labels]\" target=\"_blank\" >Speech Synthesis<\/a>\uff08<a href=\"https:\/\/www.1ai.net\/en\/tag\/tts\" title=\"_OTHER ORGANISER\" target=\"_blank\" >TTS<\/a>) Models<strong>Officially global in full<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><\/strong>I don't know. Developers can download, deploy and redevelop on this basis free of charge\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-53297\" title=\"7bea3d08j00tfh3pq0042d000u0i0p\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/05\/7bea3d08j00tfh3pq0042d000u000i0p.jpg\" alt=\"7bea3d08j00tfh3pq0042d000u0i0p\" width=\"1080\" height=\"648\" \/><\/p>\n<p>THIS OPEN-SOURCE \"SUB\" MULTI-MODULAR MODEL (27B PARAMETER SIZE) IS ORIENTED TOWARDS THE EDUCATIONAL SCENE, SUPPORTING THE MATHEMATICAL CAPABILITY OF VISUAL INPUT AND ACHIEVING THE TOP INDUSTRY LEVEL (SOTA)\u3002<\/p>\n<ul>\n<li>In the size model of the same parameter, handles a chart<strong>Hard visual math<\/strong>.<\/li>\n<li>It's a Chinese-language problem<strong>ACCURACY RATE 81.41 TP3T<\/strong>.<\/li>\n<\/ul>\n<p>IN ADDITION, THE NEW MODEL USES A FINE-TUNED THINKING CHAIN RE-ENGINEERING PROGRAMME. THE LENGTH OF THE THOUGHT CHAIN OUTPUT HAS BEEN REDUCED BY IN-DEPTH OPTIMIZATION BY BRINGING TOGETHER LARGE-SCALE, HIGH-QUALITY, STREAMLINED SAMPLES OF REASONING. THIS MEANS ANSWERING THE SAME QUESTION<strong>It's output Token, less, shorter, faster<\/strong>.<\/p>\n<p>The immediate effects for developers and enterprises doing actual business are:<strong>Decline in reasoning costs<\/strong>.<\/p>\n<p>In addition, cyber-friendly teams target students in the country<strong>Real job, test and question scene<\/strong>Depth optimization has been made to enable it to address the complex pains encountered in real learning\u3002<\/p>\n<p>AND OPEN SOURCE VOICE SYNTHESIS (TTS) MODEL SUPPORTS<strong>Translingual sound and sexual migration cloning<\/strong>If you upload a Chinese audio, you can clone the voice of the speaker and speak fluently English, Korean, Vietnamese... without a Chinese accent. And emotions can be precise in moving cloning -- if you say one word in anger, the synthetic foreign language is also angry\u3002<\/p>\n<ul>\n<li>3 seconds: Upload any audio material so that the system can complete the original copy of zero samples within 3 seconds\u3002<\/li>\n<li>97%: MORE THAN 97% IN A CLONING MISSION AND 85% IN A CLONED SOUND SIMILAR TO THE ORIGINAL\u3002<\/li>\n<li>14 languages: CE, Japan, Korea, Germany, France, West, Indonesia, Italy, Thailand, Portugal, Russia, Malay, Vietnamese, etc\u3002<\/li>\n<\/ul>\n<p>1AI WITH THE FOLLOWING TWO-PART OPEN SOURCE ADDRESSES:<\/p>\n<ul>\n<li>Multimodel model: https:\/\/huggingface.co\/netase-youudao\/Confucius4<\/li>\n<li>TTS Model: https:\/\/github.com\/netase-youudao\/Confucus4-TTS<\/li>\n<\/ul>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>ON MAY 23RD, THE INTERNET ANNOUNCED YESTERDAY THAT IT WAS DECIDED TO FORMALLY TARGET THE GLOBAL FULL-SCALE OPEN SOURCE FOR THE \"SUB\" LARGE MODEL, THE \"MULTI-MODULAR MODEL\" AND THE \"SPOKEN SYNTHESIS (TTS) MODEL, THE TWO-ENGINE CORE ENGINE OF 4.0. DEVELOPERS CAN DOWNLOAD, DEPLOY AND RE-DEVELOP ON THIS BASIS FREE OF CHARGE. THIS OPEN-SOURCE \"SUB\" MULTI-MODULAR MODEL (27B PARAMETER SIZE) IS ORIENTED TOWARDS THE EDUCATIONAL SCENE, SUPPORTING THE MATHEMATICAL CAPABILITY OF VISUAL INPUT AND ACHIEVING THE TOP INDUSTRY LEVEL (SOTA). IN THE SIZE MODEL OF THE SAME PARAMETERS, THE DIFFICULTY OF VISUAL MATHEMATICAL PROBLEMS WITH A CHART IS ADDRESSED. CHINESE-LANGUAGE MATHEMATICAL DILEMMA, ACCURACY RATE 81.4%. IN ADDITION, THE NEW MODEL USES A FINE-TUNED THINKING CHAIN RE-ENGINEERING PROGRAMME. DEPTH OPTIMIZATION BY BRINGING TOGETHER LARGE, HIGH-QUALITY, STREAMLINED SAMPLE REASONING<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[591,1096,219,1276,2102],"collection":[],"class_list":["post-53296","post","type-post","status-publish","format-standard","hentry","category-news","tag-tts","tag-1096","tag-219","tag-1276","tag-2102"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/53296","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=53296"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/53296\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=53296"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=53296"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=53296"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=53296"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}