<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: MattHart88</title><link>https://news.ycombinator.com/user?id=MattHart88</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 07 Apr 2026 05:28:39 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=MattHart88" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by MattHart88 in "Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS"]]></title><description><![CDATA[
<p>Thanks to everyone who submitted PRs! The fix is merged, new version is up.</p>
]]></description><pubDate>Mon, 06 Apr 2026 21:57:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=47667786</link><dc:creator>MattHart88</dc:creator><comments>https://news.ycombinator.com/item?id=47667786</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47667786</guid></item><item><title><![CDATA[New comment by MattHart88 in "Show HN: Ghost Pepper – 100% local hold-to-talk speech-to-text for macOS"]]></title><description><![CDATA[
<p>I've found the "corrections" feature works well for most of the jargon and misspelling use cases. Can you give it a try and let me know edge cases?</p>
]]></description><pubDate>Mon, 06 Apr 2026 21:20:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47667306</link><dc:creator>MattHart88</dc:creator><comments>https://news.ycombinator.com/item?id=47667306</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47667306</guid></item><item><title><![CDATA[New comment by MattHart88 in "Show HN: Ghost Pepper – 100% local hold-to-talk speech-to-text for macOS"]]></title><description><![CDATA[
<p>Thanks! We currently have 2 multi-lingual options available:   
- Whisper small (multilingual) (~466 MB, supports many languages)
- Parakeet v3 (25 languages) (~1.4 GB, supports 25 languages via FluidAudio)</p>
]]></description><pubDate>Mon, 06 Apr 2026 21:07:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=47667124</link><dc:creator>MattHart88</dc:creator><comments>https://news.ycombinator.com/item?id=47667124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47667124</guid></item><item><title><![CDATA[New comment by MattHart88 in "Show HN: Ghost Pepper – 100% local hold-to-talk speech-to-text for macOS"]]></title><description><![CDATA[
<p>I like this idea and it should work  -- whatever microphone you have on should be able to hear the speaker. LMK if not (e.g., are you wearing headphones? if so, the mic can't hear the speaker)</p>
]]></description><pubDate>Mon, 06 Apr 2026 21:05:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47667099</link><dc:creator>MattHart88</dc:creator><comments>https://news.ycombinator.com/item?id=47667099</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47667099</guid></item><item><title><![CDATA[Show HN: Ghost Pepper – Local hold-to-talk speech-to-text for macOS]]></title><description><![CDATA[
<p>I built this because I wanted to see how far I could get with a voice-to-text app that used 100% local models so no data left my computer. I've been using a ton for coding and emails. Experimenting with using it as a voice interface for my other agents too. 100% open-source MIT license, would love feedback, PRs, and ideas on where to take it.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47666024">https://news.ycombinator.com/item?id=47666024</a></p>
<p>Points: 307</p>
<p># Comments: 137</p>
]]></description><pubDate>Mon, 06 Apr 2026 19:50:16 +0000</pubDate><link>https://github.com/matthartman/ghost-pepper</link><dc:creator>MattHart88</dc:creator><comments>https://news.ycombinator.com/item?id=47666024</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47666024</guid></item></channel></rss>