Download Dicty
Zero-latency on-device voice dictation, meeting intelligence, and autonomous documentation sync for Windows and macOS.
Windows Setup & Quick Launch
Dicty for Windows runs on a lightweight Tauri v2 desktop shell with an embedded local Whisper AI engine.
Early Alpha Version Notice
Dicty for Windows is in active early alpha. Core local speech recognition, floating HUD, and hotkey typing are working, but you may encounter occasional bugs or unpolished edge cases. If you run into any issues, please report them on our GitHub Issues tracker so we can address them promptly!
Run the Installer
Download the setup executable and double-click to install. Dicty automatically installs to your user profile with no administrator rights required.
System Tray & Background Engine
Once launched, Dicty resides in your Windows Taskbar System Tray (notification area). Right-click the Dicty tray icon anytime to open Settings, switch prompts, check audio devices, or quit.
Dictate Anywhere via Global Hotkey
Place your cursor in any application (VS Code, Cursor, Slack, Word, browser). Press Ctrl + Space (or your custom shortcut) to trigger the floating HUD, speak, and watch your formatted text paste instantly.
High-performance offline inference using local Whisper models with zero internet required.
Reliable synthetic keystroke injection (SendInput) across all native Windows apps.
Zero voice retention. Audio is captured into memory, transcribed, and immediately discarded.
Dicty runs voice inference 100% locally on your machine (Apple Silicon GPU shaders on macOS, AVX2 CPU acceleration on Windows). Audio never leaves your computer unless you explicitly configure custom cloud LLM keys.
Need help getting started or testing the Windows Alpha?
Join our Discord community for quick troubleshooting, prompt tips, and direct feedback with the team.