<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Voice on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/voice/</link><description>Recent content in Voice on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 01 Mar 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/voice/index.xml" rel="self" type="application/rss+xml"/><item><title>Aliyun Bailian (5): Qwen-TTS for Multilingual Voice</title><link>https://www.chenk.top/en/aliyun-bailian/05-qwen-tts-voice/</link><pubDate>Sun, 01 Mar 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/aliyun-bailian/05-qwen-tts-voice/</guid><description>&lt;p>Every Chinese-language product I&amp;rsquo;ve worked on uses Qwen-TTS-Flash, not because it&amp;rsquo;s the cheapest TTS API, but because it&amp;rsquo;s the only one that handles &lt;strong>mainland Chinese dialects&lt;/strong> (Cantonese, Sichuanese, Wu) and English in the same SDK, with voices that don&amp;rsquo;t sound like a 2019 customs announcement. After six months of using it for a marketing video voice-over pipeline, this is what I wish someone had told me on day one.&lt;/p>
&lt;p>&lt;figure class="article-figure">
 &lt;img src="https://blog-pic-ck.oss-cn-beijing.aliyuncs.com/posts/en/aliyun-bailian/05-qwen-tts-voice/illustration_1.png" alt="Aliyun Bailian (5): Qwen-TTS for Multilingual Voice — Chapter overview" loading="lazy" decoding="async" class="content-image">
 
&lt;/figure>
&lt;/p></description></item></channel></rss>