<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>LiveKit on Blog by Thiyagaraj T</title>
		<link>https://thiyaga.xyz/tags/livekit/</link>
		<description>Recent content in LiveKit on Blog by Thiyagaraj T</description>
		<generator>Hugo</generator>
		<language>en</language>
		
		
		
		
			<lastBuildDate>Wed, 29 Jul 2026 00:45:00 +0530</lastBuildDate>
		
			<atom:link href="https://thiyaga.xyz/tags/livekit/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>10 Principles for Building Reliable Voice Agents on LiveKit</title>
				<link>https://thiyaga.xyz/posts/livekit-voice-agents/</link>
				<pubDate>Wed, 29 Jul 2026 00:45:00 +0530</pubDate>
				<guid>https://thiyaga.xyz/posts/livekit-voice-agents/</guid>
				<description>&lt;p&gt;Voice agent demos are easy to build. A LiveKit worker, an STT → LLM → TTS pipeline, and you have something that talks. The hard part is making it reliable.&lt;/p&gt;&#xA;&lt;p&gt;We run AI interview agents on LiveKit Cloud. An interview lasts up to an hour. A lost recording is a compliance problem. A lost transcript means the candidate has to redo the interview. A silent agent means a human sitting in an empty room, wondering if anyone is there.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
