https://pype.dev/tags/speakr/archive/atom.xml 2025-11-11T05:02:37Z All posts with the tag "speakr" Nic Payne markata-go https://pype.dev/speakr-for-recording-and-transcribing-at-home/ 2025-11-11T05:02:37Z 2025-11-11T05:02:37Z

I have been using Whisper-WebUI for several months in my homelab to record and transcribe myself thinking out loud. It's been great. Then I came across...

<p>I have been using Whisper-WebUI for several months in my homelab to record and transcribe myself thinking out loud. It&rsquo;s been great. Then I came across <a href="https://github.com/murtaza-nasir/speakr">speakr</a> which is like that but more feature rich in what I wanted out of the WebUI. Specifically I get a nicer UI with transcriptions, a chat window, built-in summarization, and diarization support (WebUI has this too but it&rsquo;s a little nicer in Speakr in my opinion).</p> <h2 id="pic"><span class="heading-wear-glyph">Pic</span> <a href="#pic" class="heading-anchor">#</a></h2> <figure> <img src="https://cdn.statically.io/gh/pypeaday/images.pype.dev/main/blog-media/20250824120404_da722d66.png" alt="20250824120404_da722d66.png"> </figure> <p>The UI is a little busy but handy for what I&rsquo;m after in the mornings or when I&rsquo;m trying to mind-dump somewhere I can conveniently explore later.</p> <h2 id="speaker-identification"><span class="heading-wear-glyph">Speaker Identification</span> <a href="#speaker-identification" class="heading-anchor">#</a></h2> <p>Requires HuggingFace Token to pull the models that perform <a href="https://en.wikipedia.org/wiki/Speaker_diarisation">Speaker diarisation</a> - ie. identifying different speakers</p> <p>Here&rsquo;s an example from an episode of Hybrid Cloud Show.</p> <figure> <img src="https://cdn.statically.io/gh/pypeaday/images.pype.dev/main/blog-media/20250826124040_48c8d2ce.png" alt="20250826124040_48c8d2ce.png"> </figure> Nic Payne https://pype.dev