{"id":342,"date":"2024-04-29T11:26:31","date_gmt":"2024-04-29T03:26:31","guid":{"rendered":"https:\/\/aitimes.link\/?p=342"},"modified":"2024-04-29T11:26:31","modified_gmt":"2024-04-29T03:26:31","slug":"myshellai-openvoice","status":"publish","type":"post","link":"https:\/\/aitimes.link\/index.php\/2024\/04\/29\/myshellai-openvoice\/","title":{"rendered":"myshell-ai\/OpenVoice"},"content":{"rendered":"\n<p><a href=\"https:\/\/github.com\/myshell-ai\/OpenVoice\">https:\/\/github.com\/myshell-ai\/OpenVoice<\/a><br>\u4e00\u4e2a\u5f00\u6e90\u7684\u591a\u8bed\u8a00 \u58f0\u97f3\u751f\u6210\u5668<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">OpenVoice V1<a href=\"https:\/\/github.com\/myshell-ai\/OpenVoice#openvoice-v1\"><\/a><\/h3>\n\n\n\n<p>As we detailed in our&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2312.01479\">paper<\/a>&nbsp;and&nbsp;<a href=\"https:\/\/research.myshell.ai\/open-voice\">website<\/a>, the advantages of OpenVoice are three-fold:<\/p>\n\n\n\n<p><strong>1. Accurate Tone Color Cloning.<\/strong>&nbsp;OpenVoice can accurately clone the reference tone color and generate speech in multiple languages and accents.<\/p>\n\n\n\n<p><strong>2. Flexible Voice Style Control.<\/strong>&nbsp;OpenVoice enables granular control over voice styles, such as emotion and accent, as well as other style parameters including rhythm, pauses, and intonation.<\/p>\n\n\n\n<p><strong>3. Zero-shot Cross-lingual Voice Cloning.<\/strong>&nbsp;Neither of the language of the generated speech nor the language of the reference speech needs to be presented in the massive-speaker multi-lingual training dataset.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">OpenVoice V2<\/h3>\n\n\n\n<p><a href=\"https:\/\/github.com\/myshell-ai\/OpenVoice#openvoice-v2\"><\/a><\/p>\n\n\n\n<p>In April 2024, we released OpenVoice V2, which includes all features in V1 and has:<\/p>\n\n\n\n<p><strong>1. Better Audio Quality.<\/strong>&nbsp;OpenVoice V2 adopts a different training strategy that delivers better audio quality.<\/p>\n\n\n\n<p><strong>2. Native Multi-lingual Support.<\/strong>&nbsp;English, Spanish, French, Chinese, Japanese and Korean are natively supported in OpenVoice V2.<\/p>\n\n\n\n<p><strong>3. Free Commercial Use.<\/strong>&nbsp;Starting from April 2024, both V2 and V1 are released under MIT License. Free for commercial use.<\/p>\n\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>https:\/\/github.com\/myshell-ai\/OpenVoice\u4e00\u4e2a\u5f00\u6e90\u7684\u591a\u8bed\u8a00 \u58f0\u97f3\u751f\u6210\u5668 O [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-342","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/342","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/comments?post=342"}],"version-history":[{"count":1,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/342\/revisions"}],"predecessor-version":[{"id":343,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/posts\/342\/revisions\/343"}],"wp:attachment":[{"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/media?parent=342"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/categories?post=342"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aitimes.link\/index.php\/wp-json\/wp\/v2\/tags?post=342"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}