voquill/voquill

Open source voice dictation technology

What it solves

Voquill is designed to replace traditional keyboard typing with voice input, allowing users to type significantly faster by dictating text into any desktop application. It addresses the common issues of filler words, false starts, and inaccurate terminology in raw voice transcriptsions.

How it works

The app operates as a cross-platform overlay with hotkeys and system integrations. Users can choose to run transcription engines like Whisper locally (with GPU acceleration) or use cloud providers. Once voice input is captured, the software uses AI to clean up the text—removing filler words and applying a personal glossary for accurate spelling of specific names and phrases. It also includes an AI assistant for voice-powered conversations.

Who it’s for

It is for desktop users on macOS, Windows, and Linux who want to increase their writing speed and professionalize their dictation through AI-driven cleanup and customization.

Highlights

  • Cross-platform support: Works across macOS, Windows, and Linux.
  • Flexible transcription: Support for local Whisper engines or cloud-based providers.
  • AI text cleanup: Automatically removes filler words and false starts.
  • Personal dictionary: Custom glossary terms and replacement rules for accuracy.
  • Privacy-focused: Option to run entirely offline for full data control.
  • AI assistant: Integrated voice-powered chat functionality.

Related

  • Project
    tover0314-w/opentypeless

    An open-source AI voice input tool for macOS, Windows, and Linux that provides context-aware dictation, AI rewriting, and one-shot voice Q&A across any desktop application.

  • Project
    moinulmoin/voicetypr

    An offline-first voice-to-text dictation app for macOS and Windows that transcribes speech and inserts it directly into any active application.

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app that converts speech to text, provides live meeting transcription with speaker diarisation, and lets you talk to AI assistants (GPT‑5, Claude, Gemini, etc.) directly from your keyboard. It works offline with Whisper‑based models or via cloud services, stores notes locally (with optional cloud sync), and offers an API for programmatic use.

  • Project
    freestyle-voice/freestyle

    An AI writing assistant that transcribes voice input into polished text and rewrites existing content, pasting the results directly at the system cursor.

  • Project
    amicalhq/amical

    A local-first, AI-powered dictation and note-taking app that uses Whisper and local LLMs to provide private, context-aware speech-to-text across desktop applications.