goodroot/hyprwhspr

• highreadme#1

  Clarify hyprwhspr's core purpose and relationship to Hyprland in the README's opening

  Why:

  CURRENT

  <h1 align="center">
      hyprwhspr
  </h1>
  
  <p align="center">
      <b>Native speech-to-text for Linux</b> - Fast, accurate and private system-wide dictation
  </p>

  COPY-PASTE FIX

  Copy

  <h1 align="center">
      hyprwhspr
  </h1>
  
  <p align="center">
      <b>Native speech-to-text for Linux</b> - Fast, accurate and private system-wide dictation
  </p>
  
  <p align="center">
      <i>While named for its excellent integration with Hyprland, hyprwhspr is a general-purpose speech-to-text solution for all Linux desktops.</i>
  </p>

  OpenDoneDismiss
• mediumreadme#2

  Add a 'Key Features & Differentiators' section to highlight unique selling points

  Why:

  CURRENT

  instant performance | Cohere / Parakeet / Whisper / Gemini / ElevenLabs / REST API | stylish visuals
  
  Built for LinuxNative AUR package for Arch, or use Debian/Ubuntu/Fedora/openSUSE
  Local, very fast defaultsInstant, private and accurate performance via in-memory models
  Latest modelsCohere Transcribe? Turbo-v3? Parakeet TDT V3? Latest and greatest
  GPU memory efficientLimit or zero memory usage easily, more for other local models
  onnx-asr for wild CPU speedsNo GPU? Optimized for great speed on any hardware
  TranslationTranslate non-English to English with a single config
  REST API or websocketsSecure, fast wires to top clouds like Gemini, ElevenLabs
  Themed visualizerVisualizes your voice, will automatch Omarchy theme
  Word overides and promptsCustom hot keys, common words, and more
  Multi-lingualGreat performance in many languages
  Long form mode with savingPause, think, resume, pause: submit... Bam!
  Auto-paste anywhereInstant paste into any active buffer, or even auto enter (optional)
  Audio ducking 🦆Reduces system volume on record (opt

  COPY-PASTE FIX

  Copy

  <h2 align="center">Key Features & Differentiators</h2>
  
  <p align="center">
      <i>hyprwhspr stands out with:</i>
  </p>
  <ul>
      <li><b>Instant Performance:</b> Local, very fast defaults for instant, private, and accurate performance via in-memory models.</li>
      <li><b>Latest Models:</b> Supports Cohere Transcribe, Turbo-v3, Parakeet TDT V3, Gemini, ElevenLabs, and other REST API integrations.</li>
      <li><b>GPU Memory Efficient:</b> Limit or zero memory usage easily, with more for other local models.</li>
      <li><b>ONNX-ASR for CPU:</b> Optimized for great speed on any hardware, even without a GPU.</li>
      <li><b>Translation:</b> Translate non-English to English with a single config.</li>
      <li><b>REST API or Websockets:</b> Secure, fast connections to top clouds like Gemini, ElevenLabs.</li>
      <li><b>Themed Visualizer:</b> Visualizes your voice, will automatch Omarchy theme.</li>
      <li><b>Word Overrides and Prompts:</b> Custom hot keys, common words, and more.</li>
      <li><b>Multi-lingual:</b> Great performance in many languages.</li>
      <li><b>Long Form Mode with Saving:</b> Pause, think, resume, pause: submit... Bam!</li>
      <li><b>Auto-paste Anywhere:</b> Instant paste into any active buffer, or even auto enter (optional).</li>
      <li><b>Audio Ducking 🦆:</b> Reduces system volume on record (optional).</li>
      <li><b>Broad Linux Support:</b> Native AUR package for Arch, or use Debian/Ubuntu/Fedora/openSUSE.</li>
  </ul>

  OpenDoneDismiss
• lowtopics#3

  Streamline repository topics to focus on core functionality and technology

  Why:

  CURRENT

  ai, archlinux, cachyos, cohere-ai, debian, dictation, elevenlabs, fedora, hyprland, omarchy, opensuse, parakeet, speech-to-text, translation, ubuntu, waybar, wayland, whisper

  COPY-PASTE FIX

  Copy

  ai, cohere-ai, dictation, elevenlabs, hyprland, parakeet, speech-to-text, translation, waybar, wayland, whisper

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  How can I get fast, private, and accurate system-wide dictation on my Linux desktop?

  you: not recommended
  AI recommended (in order):

  1. Whisper Desktop
  2. Vosk
  3. Mozilla DeepSpeech
  4. SpeechNote
  5. Kaldi

  AI recommended 5 alternatives but never named goodroot/hyprwhspr. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  What are the best options for offline speech recognition and voice input on Linux?

  you: not recommended
  AI recommended (in order):

  1. Vosk
  2. Mozilla DeepSpeech
  3. Kaldi
  4. Pocketsphinx
  5. Rhino Speech-to-Intent

  AI recommended 5 alternatives but never named goodroot/hyprwhspr. This is the gap to close.

  Show full AI answer

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of goodroot/hyprwhspr?

  pass
  ✓AI named goodroot/hyprwhspr explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts goodroot/hyprwhspr in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named goodroot/hyprwhspr explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo goodroot/hyprwhspr solve, and who is the primary audience?

  pass
  ✓AI named goodroot/hyprwhspr explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?