Show HN: VoxScribe – local, offline voice dictation for Windows (open source)

Developer ahmedhmam1994 released VoxScribe, a free open-source Windows voice dictation app that transcribes speech locally using faster-whisper on the CPU and types the result directly into the focused window. The app is triggered by a hold-to-talk global hotkey (F9 by default), performs regex-based filler-word cleanup without paid AI APIs, and makes only one network request — a one-time few-hundred-MB Whisper model download from Hugging Face on first launch. The installer is unsigned, so Windows SmartScreen shows an "unknown publisher" warning on first run, and the developer is applying for a free certificate through the SignPath Foundation's open-source program.

A free, open-source Windows desktop voice dictation app. Hold a global hotkey anywhere on your system, talk, release. Your speech is transcribed locally on your PC and typed directly into whatever window has focus. Modeled after Wispr Flow, but free and privacy-first: your voice audio is never uploaded anywhere. - Hold-to-talk hotkey F9 by default, changeable : works system-wide, in any app; change it from the tray menu's "Change Hotkey..." - Direct typing into the focused window: not clipboard/paste, so it never overwrites what you've copied - 100% local transcription: powered by faster-whisper https://github.com/SYSTRAN/faster-whisper running on your CPU; your audio never leaves your machine - Rule-based text cleanup: strips filler words "um", "uh", "like", "you know" without calling any paid AI API - Floating status indicator: small pill shows Recording/Transcribing state - Runs from the system tray: starts hidden, stays out of your way Grab the latest installer from the Releases page https://github.com/ahmedhmam1994/voxscribe-ai-voice-dictation/releases . Note on Windows SmartScreen: since VoxScribe is a new, unsigned app that hooks the keyboard for the hotkey and to type text , Windows may show a "Windows protected your PC" warning on first run. Click More info → Run anyway to proceed. This is expected for unsigned indie software and not a sign of a problem. The installer does not require admin rights per-user install . On first launch, VoxScribe downloads the Whisper speech model a few hundred MB from Hugging Face. This requires an internet connection once; after that, transcription works fully offline. - Windows 10 or 11 - A working microphone - ~1GB free disk space app + downloaded model 1. Hold F9 or your chosen hotkey, see the tray menu's "Change Hotkey..." 2. Speak 3. Release the hotkey. The transcribed, cleaned-up text is typed into whatever app you're focused in - Audio is captured, transcribed, and discarded locally: nothing is sent to a server - Text cleanup is regex-based, running entirely on your machine: no AI API calls - The only network request VoxScribe makes is the one-time Whisper model download on first run python -m venv venv venv\Scripts\pip install -r requirements.txt venv\Scripts\python.exe main.py See CLAUDE.md https://github.com/ahmedhmam1994/voxscribe-ai-voice-dictation/blob/main/CLAUDE.md for architecture notes and build/packaging commands PyInstaller + Inno Setup . The installer is currently unsigned, so Windows SmartScreen shows an "unknown publisher" warning on first run. VoxScribe is applying for a free certificate through the SignPath Foundation https://signpath.org 's open-source program: see CODE SIGNING.md https://github.com/ahmedhmam1994/voxscribe-ai-voice-dictation/blob/main/CODE SIGNING.md for the policy that program requires. Paid alternatives also work: a traditional OV/EV certificate from a CA SSL.com, Sectigo, roughly $70 to $400/yr , or Microsoft Trusted Signing https://learn.microsoft.com/en-us/azure/trusted-signing/ via Azure usage-based, no hardware token required . With any of these, run scripts\sign release.ps1 after building; see that script's header comment for exact usage.