<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Whisper on tjnome</title><link>https://tjnome.no/tags/whisper/</link><description>Recent content in Whisper on tjnome</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 12 Mar 2026 20:00:00 -0700</lastBuildDate><atom:link href="https://tjnome.no/tags/whisper/index.xml" rel="self" type="application/rss+xml"/><item><title>TJvox: macOS-Style Dictation for Linux</title><link>https://tjnome.no/projects/tjvox/</link><pubDate>Thu, 12 Mar 2026 20:00:00 -0700</pubDate><guid>https://tjnome.no/projects/tjvox/</guid><description>&lt;p class="intro-paragraph"&gt;I type a lot. Emails, code, chat messages, angry comments on the internet. My wrists were starting to file complaints. macOS has this delightful built-in dictation feature where you double-tap a key, speak, and it types for you. Linux... did not. At least not in a way that didn't involve shouting at a browser tab or paying some cloud API by the syllable. So I built my own.&lt;/p&gt;
&lt;h2 id="what-it-does"&gt;
 What It Does
 &lt;a href="#what-it-does" class="heading-anchor" aria-hidden="true" tabindex="-1"&gt;#&lt;/a&gt;
&lt;/h2&gt;
&lt;p&gt;&lt;strong&gt;TJvox&lt;/strong&gt; is a local, offline voice dictation app for Linux (Wayland-first, because that&amp;rsquo;s what I run). Hit a hotkey, speak, and it transcribes your rambling into text using OpenAI&amp;rsquo;s Whisper — running entirely on your own machine. No data leaves the house.&lt;/p&gt;</description></item></channel></rss>