<?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 Monte&#39;s Snippets</title>
    <link>https://montepy.in/categories/voice/</link>
    <description>Recent content in Voice on Monte&#39;s Snippets</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Tue, 15 Sep 2026 21:09:49 +0530</lastBuildDate>
    <atom:link href="https://montepy.in/categories/voice/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Gemini Tool Call</title>
      <link>https://montepy.in/posts/gemini-tool-call/</link>
      <pubDate>Tue, 15 Sep 2026 21:09:49 +0530</pubDate>
      <guid>https://montepy.in/posts/gemini-tool-call/</guid>
      <description>&lt;p&gt;Working with &lt;code&gt;gemini-live-2.5-flash-native-audio&lt;/code&gt; (of course, naming things is not Google&amp;rsquo;s strongest suit—remember Bard?) has its own ups and downs. No doubt, the liveliness, expressiveness, and language capabilities are really good, but tool (function) calling had me thinking otherwise.&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;Reducing unintentional tool calls is especially important for our use case, as it involves taking images via voice commands. A photo taken unintentionally makes it look like the device is taking photos by itself.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
