<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>speech-to-text on Saurabh Kumar</title><link>https://saurabh-kumar.com/tags/speech-to-text/</link><description>Recent content in speech-to-text on Saurabh Kumar</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright © 2025, Saurabh Kumar.</copyright><lastBuildDate>Thu, 08 Oct 2026 12:00:00 +0000</lastBuildDate><atom:link href="https://saurabh-kumar.com/tags/speech-to-text/index.xml" rel="self" type="application/rss+xml"/><item><title>Wispr Flow</title><link>https://saurabh-kumar.com/til/1791460800/</link><pubDate>Thu, 08 Oct 2026 12:00:00 +0000</pubDate><guid>https://saurabh-kumar.com/til/1791460800/</guid><description>&lt;p&gt;Back on &lt;a href="https://wisprflow.ai/" rel="noopener external"&gt;Wispr Flow&lt;/a&gt; after six months on local speech-to-text (&lt;a href="https://github.com/altic-dev/FluidVoice" rel="noopener external"&gt;FluidVoice&lt;/a&gt; with Parakeet, plus Whisper). Local transcription is fine. The cleanup is what&amp;rsquo;s missing: fixing misheard jargon ate the time dictation saved. Flow&amp;rsquo;s correction pass, OS-level integration and phone keyboard win. It matters more now because models follow high-level intent well: I speak the intent plus constraints in one go and let the LLM structure it. Whisper mode works even when you speak softly. Want to try it? My &lt;a href="https://wisprflow.ai/r?SAURABH2220" rel="noopener external"&gt;referral link&lt;/a&gt; gets you a free month of Pro, and I get one once you&amp;rsquo;ve dictated 2,000 words.&lt;/p&gt;&#10;</description></item><item><title>FluidVoice</title><link>https://saurabh-kumar.com/til/1775995201/</link><pubDate>Sun, 12 Apr 2026 12:00:01 +0000</pubDate><guid>https://saurabh-kumar.com/til/1775995201/</guid><description>&lt;p&gt;&lt;a href="https://github.com/altic-dev/FluidVoice" rel="noopener external"&gt;FluidVoice&lt;/a&gt; with paraquet v2 is soemthing i&amp;rsquo;ve been using now as my default speech-to-text on Mac, after evaluating WisperFlow, Handy and VoiceInk.&lt;/p&gt;&#10;</description></item><item><title>Handy</title><link>https://saurabh-kumar.com/til/1770897600/</link><pubDate>Thu, 12 Feb 2026 12:00:00 +0000</pubDate><guid>https://saurabh-kumar.com/til/1770897600/</guid><description>&lt;p&gt;&lt;a href="https://handy.computer/" rel="noopener external"&gt;Handy&lt;/a&gt; Looks like a promising tool for to replace WisperFlow and VoiceInk for speech to text conversion. &lt;a href="https://dannysmith.notion.site/Danny-s-Software-313c769fa9c04819a37d813da0485c78" rel="noopener external"&gt;via&lt;/a&gt;&lt;/p&gt;&#10;</description></item><item><title>VoiceLink</title><link>https://saurabh-kumar.com/til/1768219201/</link><pubDate>Mon, 12 Jan 2026 12:00:01 +0000</pubDate><guid>https://saurabh-kumar.com/til/1768219201/</guid><description>&lt;p&gt;Learnt about &lt;a href="https://tryvoiceink.com/" rel="noopener external"&gt;VoiceLink&lt;/a&gt;, an alternative to [Wispr Flow] that have been using as my STT software, with it&amp;rsquo;s pricing model VoiceLink might be better replacement if it performs as good as WisprFlow&lt;/p&gt;&#10;</description></item></channel></rss>