<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[试一试用ai 把 王祖贤 还原成香港配音(LTX2.3 &amp; SOULX-SINGER)]]></title><description><![CDATA[<p dir="auto">前文：<br />
在网上看到王祖贤的视频，才发觉人家原音跟我们平时看港片的时候不一样的，<br />
我现在试一试，看看使用ai, 可否还原当年的音调吗</p>
<hr />
<h3>做法流程：</h3>
<p dir="auto">1  首先我的做法是这样，先想办法找到当年王祖贤的港片，然后截取10秒的视频，<br />
2 将该视频转成mp3， 将王祖贤现在的视频转成mp3。。<br />
3 将mp3 克隆，然后按照王祖贤现在的mp3播放出来。。<br />
4 把已经克隆出来的mp3, 使用premier pro, 替换掉原本mp4里面的音频<br />
5 输出就可以</p>
<hr />
<p dir="auto">这是我王祖贤原本的素材</p>
<p dir="auto">王祖贤原音 去硅谷<br />
<a href="https://youtube.com/shorts/2hweDAF_gek?feature=share" rel="nofollow ugc">https://youtube.com/shorts/2hweDAF_gek?feature=share</a></p>
<p dir="auto">王祖贤 香港配音<br />
<a href="https://youtube.com/shorts/6xG0vTzc0xs?feature=share" rel="nofollow ugc">https://youtube.com/shorts/6xG0vTzc0xs?feature=share</a></p>
<p dir="auto">这个是已经处理过的，王祖贤配音 去硅谷<br />
<a href="https://youtube.com/shorts/QRTueSnK5QE?feature=share" rel="nofollow ugc">https://youtube.com/shorts/QRTueSnK5QE?feature=share</a></p>
<hr />
<h3>需要的工具</h3>
<h3>1 一部手机当作截取视频工具</h3>
<p dir="auto"><img src="https://upload.lcz.me/uploads/a9091b75-fd45-4d93-98f8-4306ed0d891c.png" alt="Screenshot 2026-06-21 101323.png" class=" img-fluid img-markdown" /></p>
<h3>2 audacity 将视频转成 mp3</h3>
<p dir="auto"><img src="https://upload.lcz.me/uploads/699f2a75-c508-4aa2-9931-a094ed7ae848.png" alt="Screenshot 2026-06-21 101456.png" class=" img-fluid img-markdown" /></p>
<p dir="auto"><a href="https://www.audacityteam.org/download/" rel="nofollow ugc">https://www.audacityteam.org/download/</a></p>
<h3>3 将mp3 克隆，然后按照王祖贤现在的mp3播放出来。。</h3>
<p dir="auto"><img src="https://upload.lcz.me/uploads/cf70beb5-67b8-4db7-b264-516858e729ba.png" alt="Screenshot 2026-06-21 101719.png" class=" img-fluid img-markdown" /></p>
<p dir="auto"><a href="https://github.com/Soul-AILab/SoulX-Singer" rel="nofollow ugc">https://github.com/Soul-AILab/SoulX-Singer</a></p>
<h3>4 把已经克隆出来的mp3, 使用premier pro, 替换掉原本mp4里面的音频</h3>
<p dir="auto"><img src="https://upload.lcz.me/uploads/32fffb1d-ab4a-4e68-b5cd-fdbdd8338d58.png" alt="Screenshot 2026-06-21 090926.png" class=" img-fluid img-markdown" /></p>
<h3>5 这个是已经处理过的，王祖贤配音 去硅谷</h3>
<p dir="auto"><a href="https://youtube.com/shorts/QRTueSnK5QE?feature=share" rel="nofollow ugc">https://youtube.com/shorts/QRTueSnK5QE?feature=share</a></p>
<h3>bonus</h3>
<p dir="auto">其中有一个技巧是，在音频素材尽量只是保留人声，完美去除背景声，这样就必须利用另外一个ai 输出纯人声vocal</p>
<p dir="auto"><img src="https://upload.lcz.me/uploads/552ce114-69ac-4aeb-a234-3c271ba2e3fd.png" alt="Screenshot 2026-06-21 090644.png" class=" img-fluid img-markdown" /></p>
<p dir="auto">（记得save as 下载，把json 改成zip) <a href="https://upload.lcz.me/uploads/539ef5a6-c544-4f30-ae08-6d2da7459175.json" rel="nofollow ugc">yt2mkv_tools2-12.json</a></p>
]]></description><link>https://lcz.me/topic/641/试一试用ai-把-王祖贤-还原成香港配音-ltx2.3-soulx-singer</link><generator>RSS for Node</generator><lastBuildDate>Wed, 01 Jul 2026 14:46:19 GMT</lastBuildDate><atom:link href="https://lcz.me/topic/641.rss" rel="self" type="application/rss+xml"/><pubDate>Sun, 21 Jun 2026 02:24:34 GMT</pubDate><ttl>60</ttl><item><title><![CDATA[Reply to 试一试用ai 把 王祖贤 还原成香港配音(LTX2.3 &amp; SOULX-SINGER) on Sun, 21 Jun 2026 02:55:23 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/terry" aria-label="Profile: terry">@<bdi>terry</bdi></a></p>
<p dir="auto">因为他们都是py, 我已经做成自动工作流了，</p>
<p dir="auto">就差在两步，audacity 输出mp3 &amp; premier pro自动结合</p>
<p dir="auto">我的构思是，跟ai 说，把这段视频（1）转成视频（2）的声音。。</p>
]]></description><link>https://lcz.me/post/7652</link><guid isPermaLink="true">https://lcz.me/post/7652</guid><dc:creator><![CDATA[imbiplaza ASUS]]></dc:creator><pubDate>Sun, 21 Jun 2026 02:55:23 GMT</pubDate></item><item><title><![CDATA[Reply to 试一试用ai 把 王祖贤 还原成香港配音(LTX2.3 &amp; SOULX-SINGER) on Sun, 21 Jun 2026 02:49:39 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/imbiplaza-asus" aria-label="Profile: imbiplaza-ASUS">@<bdi>imbiplaza-ASUS</bdi></a> 不能，它不是替换，而是克隆音色，然后让AI用这种腔调说话，和你这个替换是不同的。</p>
]]></description><link>https://lcz.me/post/7651</link><guid isPermaLink="true">https://lcz.me/post/7651</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Sun, 21 Jun 2026 02:49:39 GMT</pubDate></item><item><title><![CDATA[Reply to 试一试用ai 把 王祖贤 还原成香港配音(LTX2.3 &amp; SOULX-SINGER) on Sun, 21 Jun 2026 02:43:39 GMT]]></title><description><![CDATA[<p dir="auto"><a class="plugin-mentions-user plugin-mentions-a" href="/user/terry" aria-label="Profile: terry">@<bdi>terry</bdi></a><br />
audacity 足够简单，足够快</p>
<p dir="auto">voxcpm 也是可以克隆，但是我暂时还没研究到，他到底能不能照版煮碗把已经克隆出来的音频放入原本时间段</p>
]]></description><link>https://lcz.me/post/7650</link><guid isPermaLink="true">https://lcz.me/post/7650</guid><dc:creator><![CDATA[imbiplaza ASUS]]></dc:creator><pubDate>Sun, 21 Jun 2026 02:43:39 GMT</pubDate></item><item><title><![CDATA[Reply to 试一试用ai 把 王祖贤 还原成香港配音(LTX2.3 &amp; SOULX-SINGER) on Sun, 21 Jun 2026 02:40:34 GMT]]></title><description><![CDATA[<p dir="auto">很牛逼，很专业，连audacity这种上古神器都给整出来了，我的意思是，为啥不用剪映分离人声，然后交给voxcpm克隆呢？<img src="https://lcz.me/assets/plugins/nodebb-plugin-emoji/emoji/android/1f602.png?v=9a87c0a6150" class="not-responsive emoji emoji-android emoji--joy" style="height:23px;width:auto;vertical-align:middle" title="😂" alt="😂" /></p>
]]></description><link>https://lcz.me/post/7649</link><guid isPermaLink="true">https://lcz.me/post/7649</guid><dc:creator><![CDATA[terry]]></dc:creator><pubDate>Sun, 21 Jun 2026 02:40:34 GMT</pubDate></item></channel></rss>