<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Voice-Cloning on IT News</title>
    <link>https://it-news.uk/tags/voice-cloning/</link>
    <description>Recent content in Voice-Cloning on IT News</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 23 Jun 2026 00:00:00 +0800</lastBuildDate>
    <atom:link href="https://it-news.uk/tags/voice-cloning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>NetEase Open-Sources Confucius4-TTS: 3-Second Voice Cloning Across 14 Languages, Zero Accent</title>
      <link>https://it-news.uk/posts/netease-open-sources-confucius4-tts/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0800</pubDate>
      <guid>https://it-news.uk/posts/netease-open-sources-confucius4-tts/</guid>
      <description>&lt;p&gt;NetEase Youdao has thrown open the doors on one of the most ambitious voice AI projects to date, announcing the full open-source release of Confucius4-TTS — the &amp;ldquo;Ziyue 4.0&amp;rdquo; text-to-speech engine that can clone a human voice from just three seconds of audio and reproduce it across 14 languages with zero detectable accent. It is, the company claims, the first open-source model to achieve cross-lingual, accent-free voice cloning without requiring reference text.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
