A cross-platform speech-to-text engine that works in every app. Dictate into Slack, your browser, your IDE — anything with a text field. macOS, Windows, and Linux.
Default hotkey: CTRL + SHIFT + L (or customize it)
Press a hotkey, speak, and your words appear as text — right where your cursor is. No app switching, no typing, no copy-pasting.
A sleek overlay appears wherever you are. No window switching, no interruptions.
Talk like you normally would. HeyDict transcribes your speech in real time, right as you speak.
Your words are injected directly into the active text field. Any app, any window, any OS.
HeyDict is a native speech-to-text engine that runs on macOS, Windows, and Linux. Dictate into any app with a text field — from your browser to your terminal.
HeyDict injects your transcribed text directly into the active window via clipboard and accessibility APIs. If it has a text cursor, HeyDict works there.
Native builds for all three major platforms. Same experience, same hotkey, same quality — no matter your OS.
Powered by Whisper & Moonshine running locally. Your audio never leaves your device. No cloud, no accounts, no data collection.
HeyDict exposes a robust plugin interface so developers can build custom voice-powered workflows on top of a solid STT foundation. Create plugins for your tools, share them with the community, or keep them private.
HeyDict transcribes your voice entirely on your machine. No audio is ever uploaded. And because it's fully open source, you can verify every line of code yourself.
HeyDict's core voice engine is free and open source. Go further with Pro features.
The full local voice engine. No limits, no strings.
Everything in Free, plus the full agent stack.
Cancel anytime. No lock-in.
Dictate into any app on any platform. Free, private, open source, and extensible with plugins.