<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Voice-Assistant on Arash Taher</title>
    <link>https://arashtaher.com/tags/voice-assistant/</link>
    <description>Recent content in Voice-Assistant on Arash Taher</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 11 Sep 2026 11:35:00 +0000</lastBuildDate>
    <atom:link href="https://arashtaher.com/tags/voice-assistant/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Learning local LLMs for an offline voice assistant</title>
      <link>https://arashtaher.com/blog/learning-local-llms-for-an-offline-voice-assistant/</link>
      <pubDate>Fri, 11 Sep 2026 11:35:00 +0000</pubDate>
      <guid>https://arashtaher.com/blog/learning-local-llms-for-an-offline-voice-assistant/</guid>
      <description>&lt;p&gt;With the recent developments in local LLMs, building an offline voice assistant that actually works started to feel like a plausible idea. I was also looking for a project that would teach me how to build LLM-based applications that can run on the edge.&lt;/p&gt;&#xA;&lt;p&gt;This is a short summary of that journey: from knowing very little about running inference to having a quantized, optimized voice assistant running on my machine.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
