Dictating email on Mac
Email is mostly typing. With WhisprDesk you click into the message, press the hotkey, and speak your reply. The text appears at your cursor in any text field where you can paste, whether that is a mail app or a webmail page in your browser.
Reply in a few sentences
Open the reply, click into the body, press the hotkey, and say what you want to say. Press it again to stop. Read it once, fix anything you want, and send. Tap mode (press once to start and once to stop) is the default; Hold mode works like a walkie-talkie.
Polish the tone
If you turn on AI cleanup, you can give a spoken instruction with the agent name, for example "Hey WhisprDesk, make this sound more formal." The AI follows it and pastes the result. Cleanup is optional and off by default, and the model can be local or a cloud provider using your own key.
Names and addresses
Add colleagues' names and company terms to the Dictionary to help Whisper and cloud models recognize them. Dictation fills the body; you will still type or pick the recipient's address yourself.
What stays on your Mac
Where your voice goes depends on the engine you choose. With a local model (NVIDIA Parakeet is about 680 MB), transcription runs on your Mac and your audio is not uploaded. With a cloud provider, your audio goes directly to the provider whose key you entered. WhisprDesk does not receive it either way.
Frequently asked questions
- Does it work with my email app?
- It pastes into whichever app has focus, so it works in any text field where you can paste. It needs the Accessibility permission. Without it, the text is copied and you paste it yourself with Cmd+V.
- Does it send anything automatically?
- No. It only puts text into the field. You review and send the message yourself.
- Does it work for password fields?
- Some secure fields, such as password boxes, block automatic pasting.