<?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>Voice on alelec blog</title>
    <link>https://notes.alelec.net/tags/voice/</link>
    <description>Recent content in Voice on alelec blog</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 05 Apr 2026 08:30:00 +1000</lastBuildDate>
    <atom:link href="https://notes.alelec.net/tags/voice/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Getting Qwen3-ASR into Handy, 114 experiments deep</title>
      <link>https://notes.alelec.net/posts/qwen3-asr-in-handy/</link>
      <pubDate>Sun, 05 Apr 2026 08:30:00 +1000</pubDate>
      <guid>https://notes.alelec.net/posts/qwen3-asr-in-handy/</guid>
      <description>&lt;p&gt;&lt;img alt=&#34;A man sits on a park bench with a laptop on his lap, dictating quietly, a jogger passing in the background&#34; loading=&#34;lazy&#34; src=&#34;https://notes.alelec.net/assets/qwen3-handy-hero.jpeg&#34;&gt;&lt;/p&gt;
&lt;p&gt;Handy is a local voice-to-text desktop app by @cjpais that I&amp;rsquo;ve been contributing to for a few months. Push a key, speak, release, and whatever you said appears at the cursor. No cloud, no API key, no latency across the wire. The transcription is done by &lt;a href=&#34;https://github.com/cjpais/transcribe-rs&#34;&gt;transcribe-rs&lt;/a&gt;, a Rust crate that wraps a handful of ASR engines (whisper, Parakeet, SenseVoice, Canary, openai) behind a unified interface.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
