<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Edge on Fulloch</title><link>https://fulloch.com/tags/edge/</link><description>Recent content in Edge on Fulloch</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Liam Pettigrew</copyright><lastBuildDate>Sat, 11 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://fulloch.com/tags/edge/index.xml" rel="self" type="application/rss+xml"/><item><title>Getting Voice Onto a CPU (Part 2): More Attempts at Qwen3 TTS</title><link>https://fulloch.com/posts/getting-voice-onto-a-cpu-part-2/</link><pubDate>Sat, 11 Jul 2026 00:00:00 +0000</pubDate><guid>https://fulloch.com/posts/getting-voice-onto-a-cpu-part-2/</guid><description>ONNX quantisation tuning produced great RTF numbers and unusable audio. A GGUF runtime with worse numbers won on the only test that mattered.</description></item><item><title>Getting Voice Onto a CPU: CPU-Only ASR and TTS for Fulloch</title><link>https://fulloch.com/posts/getting-voice-onto-a-cpu/</link><pubDate>Fri, 26 Jun 2026 00:00:00 +0000</pubDate><guid>https://fulloch.com/posts/getting-voice-onto-a-cpu/</guid><description>How Fulloch&amp;rsquo;s CPU tier runs speech recognition and text-to-speech on a CPU-only PC</description></item></channel></rss>