<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Kokoro on Victor Salles</title><link>https://victorsalles.com/en/tags/kokoro/</link><description>Recent content in Kokoro on Victor Salles</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 22 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://victorsalles.com/en/tags/kokoro/index.xml" rel="self" type="application/rss+xml"/><item><title>Building an Offline Voice System for macOS</title><link>https://victorsalles.com/en/posts/building-offline-voice-system-macos/</link><pubDate>Sun, 22 Mar 2026 00:00:00 +0000</pubDate><guid>https://victorsalles.com/en/posts/building-offline-voice-system-macos/</guid><description>How I built a fully offline text-to-speech and speech-to-text system for macOS using Kokoro-82M and mlx-whisper — no cloud APIs, streaming audio in under a second.</description></item></channel></rss>