Handy puts local speech transcription into the text field you are already using
Handy records a shortcut-triggered utterance, transcribes it on your computer and pastes the words into the active app. The free open-source tool supports Windows, macOS and Linux.
Your speech can become text without making a round trip through a cloud transcription service. Handy’s README describes a shortcut that records while held, or toggles recording on and off, then puts the transcript into the app you are using.
The README calls the process “entirely local.” The project lists Whisper options and a CPU-optimized Parakeet model, with GPU acceleration available for Whisper where supported. Its setup calls for microphone and accessibility permissions.
The paste step deserves as much attention as the model. Text has to reach the focused app, and clipboard-based delivery may expose it to clipboard history or syncing tools you have enabled. That is a consequence of where the words go, rather than a claim that Handy uploads the recording. An email editor or cloud document can transmit the resulting text even when transcription itself stayed local.
The next useful comparison is a few minutes of your own speech, including the names and technical words you actually need. A model list cannot tell you how much correcting your day will require.