{"id":52748,"date":"2026-05-08T11:57:43","date_gmt":"2026-05-08T03:57:43","guid":{"rendered":"https:\/\/www.1ai.net\/?p=52748"},"modified":"2026-05-08T11:57:43","modified_gmt":"2026-05-08T03:57:43","slug":"%e5%b0%8f%e7%b1%b3%e5%bc%80%e6%ba%90-omnivoice-%e5%a4%9a%e8%af%ad%e8%a8%80%e8%af%ad%e9%9f%b3%e5%85%8b%e9%9a%86-tts","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/52748.html","title":{"rendered":"OmniVoice Multilingual Voice Cloning TTS"},"content":{"rendered":"<p>May 8th news, yesterday<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%b0%8f%e7%b1%b3\" title=\"[View articles tagged with [Xiaomi]]\" target=\"_blank\" >Millet<\/a> AI LABORATORY RELEASE AND<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>polyglot<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%af%ad%e9%9f%b3%e5%85%8b%e9%9a%86\" title=\"[Sees articles with tags]\" target=\"_blank\" >Voice cloning<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/tts\" title=\"_OTHER ORGANISER\" target=\"_blank\" >TTS<\/a> Model OmniVoice, a team of 580,000 hours of training based on 50 open source data sets covering 646 languages\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-52749\" title=\"42afda8cj00tep9ly0016d000sh00e9m\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2026\/05\/42afda8cj00tep9ly0016d000sh00e9m.jpg\" alt=\"42afda8cj00tep9ly0016d000sh00e9m\" width=\"1025\" height=\"513\" \/><\/p>\n<p>The quality of Chinese and English synthesis is better than that of the dominant model, and the rate of reasoning is 40 times that in real time<\/p>\n<p>In 24 languages, speech similarities and understandings go beyond multiple commercial systems<\/p>\n<p>In 102 languages, understanding is close to real voice, and even small languages with less than 10 hours of training can be properly synthesized\u3002<\/p>\n<p>In addition to voice cloning, OmniVoice also supports the use of word descriptions to specify the sound (e.g. \"Women, Young People, Sichuan language \" ), which automatically filters the noise in the reference audio, and supports the insertion of speech symbols such as laughter, sighs and so forth, as well as the manual correction of polyphonic pronunciations\u3002<\/p>\n<p>\ud83d\udcbb GitHub: github.com\/k2-fsa\/OmniVoice<\/p>\n<p>Hugging Face: hugglingface.co\/k2-fsa\/OmniVoice<\/p>","protected":false},"excerpt":{"rendered":"<p>News of 8 May, yesterday, Mi AI laboratory released and opened-source multi-language voice cloning TTS model OmniVoice, and the team built 580,000 hours of training data based on 50 open-source data sets covering 646 languages. The Chinese-English synthesis quality is better than that of the dominant model, and the rate of reasoning is 40 times the speed of real time; In 24 languages, it is more like and understandable than in multiple commercial systems; In 102 languages, it is close to real voice, even in small languages with less than 10 hours of training data. In addition to voice cloning, OmniVoice supports the use of word description to specify the sound (e.g. \"Women, Youth, Sichuanese\"), which automatically filters the noise in the reference audio<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[591,1114,219,2110],"collection":[],"class_list":["post-52748","post","type-post","status-publish","format-standard","hentry","category-news","tag-tts","tag-1114","tag-219","tag-2110"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/52748","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=52748"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/52748\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=52748"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=52748"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=52748"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=52748"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}