LesskeysWhisper on a Mac: run it offline, step by step
Yes, Whisper runs offline on a Mac with no setup: an app such as Lesskeys has a Whisper speech model built in, so you press a hotkey to dictate or add a file to transcribe. The audio never leaves the Mac, and there is no account.
macOS 13+ on Apple Silicon · No subscription
Last reviewed
Step by step
Run Whisper on your Mac in four steps
- Install Lesskeys from the Mac App Store, or use Download for Mac. It needs macOS 13 or later on an Apple Silicon Mac (M1 or newer). A starter model is inside, so nothing else is needed.
- To dictate, click where the text should go, hold the Lesskeys dictation hotkey and talk, then release it and paste.
- To transcribe a recording, choose Transcribe and add the audio or video file. The first time there is a small extra download; after that it needs no internet.
- Open the transcript from Library. To check it ran on your Mac, switch Wi-Fi off and repeat.
Which model to pick is measured in Which Whisper model to run on a Mac, and how each holds up outside English in Whisper accuracy in 29 languages.
What it is
What is Whisper?
An open-source speech-to-text model that can run entirely on your own computer.
That is why it became the usual choice for transcribing without uploading; how local transcription works explains what runs where.
- Offlineonce the model is on your Mac
- No accountneeded
- Nothinguploaded
Two ways
Two ways to run it, side by side
| What | A command-line tool | Lesskeys |
|---|---|---|
| Setup | Several manual steps: install, download, convert, run | Install the app; a starter model is inside it |
| Dictate into any app | No built-in way | Yes, with a hotkey |
| Transcribe a recorded call | A file at a time, after you record it | Records the call and transcribes it; no bot joins the call |
| Speaker labels | Not built in. An experimental option (tinydiarize) needs a special English model and marks where the speaker changes, not who spoke | Yes: you set how many people spoke, and each voice gets its own label |
Whisper writes only the words; speaker labels come from a separate step, covered in speaker diarization on a Mac.
Tell the people you record; some places require everyone's consent.
Sources, read on 15 October 2026
- whisper.cpp, the open-source project (the command-line route in the table, speaker segmentation via tinydiarize (experimental))
Questions
Questions about Whisper on a Mac
Does Whisper cost anything to run on a Mac?
Whisper is open source, so running it yourself carries no licence fee. Apps built on it set their own terms.
Does Whisper work offline on a Mac?
Yes. Once the model is downloaded, Whisper transcribes entirely on your Mac with no internet connection, and your audio never leaves the device.
Do I need the command line to use Whisper?
No. The command line is the technical route. If you would rather not set that up, an app such as Lesskeys runs Whisper for you and adds dictation, call transcription and speaker labels.
Is Lesskeys the same as Whisper?
No. Lesskeys runs Whisper on your Mac and wraps it with system-wide dictation, call and video transcription and speaker labels, all offline. It is an app around the models, not the models themselves.
More