<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>Voice Pipes blog</title>
    <link>https://voicepipes.app/blog</link>
    <description>News and notes from the people building Voice Pipes.</description>
    <language>en</language>
    <item>
      <title>Treat audio like a page</title>
      <link>https://voicepipes.app/blog/treat-audio-like-a-page</link>
      <guid>https://voicepipes.app/blog/treat-audio-like-a-page</guid>
      <pubDate>Sat, 03 Oct 2026 09:00:00 GMT</pubDate>
      <description>When I read along while something is read to me, I want to move through the voice the way my eyes move through a page: skim what I know, slow down for the hard part, go back and hear it again. Here's how the read-along keys in Voice Pipes let me do that.</description>
    </item>
    <item>
      <title>Read it to me</title>
      <link>https://voicepipes.app/blog/read-it-to-me</link>
      <guid>https://voicepipes.app/blog/read-it-to-me</guid>
      <pubDate>Fri, 02 Oct 2026 15:00:00 GMT</pubDate>
      <description>I wanted my agent to speak up when it has something worth hearing, not on every reply, and to show me the words as it reads, so I can jump around, change the speed and stop when I've heard enough. Here's how Voice Pipes does it, through one command line.</description>
    </item>
    <item>
      <title>Why I built Voice Pipes</title>
      <link>https://voicepipes.app/blog/why-i-built-voice-pipes</link>
      <guid>https://voicepipes.app/blog/why-i-built-voice-pipes</guid>
      <pubDate>Fri, 02 Oct 2026 00:00:00 GMT</pubDate>
      <description>One button and one pipeline weren't enough. I wanted a fast local path and a careful one, a voice that reads back, my own logic anywhere in the pipe, no subscription, and a tool my agents can drive.</description>
    </item>
  </channel>
</rss>
