<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>TTS on NoRaincheck</title><link>https://noraincheck.github.io/tags/tts/</link><description>Recent content in TTS on NoRaincheck</description><generator>Hugo</generator><language>en-US</language><copyright>NoRaincheck</copyright><lastBuildDate>Sun, 01 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://noraincheck.github.io/tags/tts/index.xml" rel="self" type="application/rss+xml"/><item><title>Maya1 vs Kokoro vs Kitten TTS Review</title><link>https://noraincheck.github.io/posts/maya1-vs-kokoro-vs-kitten-tts-review/</link><pubDate>Sun, 01 Mar 2026 00:00:00 +0000</pubDate><guid>https://noraincheck.github.io/posts/maya1-vs-kokoro-vs-kitten-tts-review/</guid><description>&lt;h2 id="maya1-vs-kokoro-vs-kitten-tts-review"&gt;Maya1 vs Kokoro vs Kitten TTS Review&lt;/h2&gt;&#10;&lt;p&gt;&lt;em&gt;March 2026&lt;/em&gt;&lt;/p&gt;&#10;&lt;p&gt;I finally got to test TTS models, and got them running locally with a variety of&#10;notes.&lt;/p&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;Kitten: advertised as the smallest model, its also the easiest to setup&lt;/li&gt;&#10;&lt;li&gt;Kokoro: an extremely good model for its size. I found getting it setup with&#10;the onnx wrapping to be the most straightforward (supports quants!)&lt;/li&gt;&#10;&lt;li&gt;Maya1: supports gguf. I ended up hosting it in LM Studio with a wrapper to&#10;have it working. This is the best quality but also the slowest&lt;/li&gt;&#10;&lt;/ul&gt;&#10;&lt;p&gt;TLDR: Use Kokoro if you want a good balance of speed and quality, otherwise&#10;Maya1 is a suitable model if you&amp;rsquo;re willing to wait a bit&lt;/p&gt;</description></item></channel></rss>