<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Voice on NicoLabs</title>
		<link>https://blog.hellonico.info/tags/voice/</link>
		<description>Recent content in Voice on NicoLabs</description>
		<generator>Hugo</generator>
		<language>en</language>
		
		
		
		
			<lastBuildDate>Sun, 11 Oct 2026 15:20:00 +0900</lastBuildDate>
		
			<atom:link href="https://blog.hellonico.info/tags/voice/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Giving Ollama a Mouth, Ears, and a 3.5-Inch Screen: Building a Voice-First Pocket Terminal AI with Coni &amp; Whisper</title>
				<link>https://blog.hellonico.info/posts/voice-touch-ollama-terminal-pi4/</link>
				<pubDate>Sun, 11 Oct 2026 15:20:00 +0900</pubDate>
				<guid>https://blog.hellonico.info/posts/voice-touch-ollama-terminal-pi4/</guid>
				<description>&lt;p&gt;Let’s take a look at the state of conversational AI today.&lt;/p&gt;&#xA;&lt;p&gt;If you want to talk to an LLM, the tech industry usually insists you follow one of two paths:&lt;/p&gt;&#xA;&lt;ol&gt;&#xA;&lt;li&gt;Open a web browser, load a 250MB single-page JavaScript application, agree to eight privacy policies, and hand your credit card to an API that bills you $0.03 for every syllable.&lt;/li&gt;&#xA;&lt;li&gt;Install an Electron desktop app that devours 1.8 GB of RAM before it even finishes rendering its animated microphone widget.&lt;/li&gt;&#xA;&lt;/ol&gt;&#xA;&lt;p&gt;Whatever happened to &lt;strong&gt;small, dedicated, delightful computing devices&lt;/strong&gt;? The kind of hardware gadgets you pick up with one hand, tap a button, talk to, and get an instant, unfiltered answer—without corporate telemetry or subscriptions?&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
