Saywind privacy policy

Last updated: 18 October 2026

Saywind is a dictation app for the Mac. It is published by Peiser Apcar LTD (“we”, “us”), a company registered in the UK.

In short

• Saywind runs entirely on your Mac.
• Your audio and text never leave your Mac.
• There’s no analytics, no tracking and no account.
• Saywind uses the network for two things only: downloading speech models the first time each is needed, and checking for a newer version at most once a day.

Your voice and your words

Speech recognition runs on your Mac, on its Neural Engine. Saywind never sends your audio or your text anywhere, so we never see them. When Saywind pastes text into another app, that app handles it like anything you type.

Saywind hears you only while you hold the dictation key, or while hands-free mode is on. With Instant start on, the microphone stays ready between dictations, but muted, as explained below.

Instant start

Instant start is on by default. You can turn it off in Settings.

A microphone can take a moment to wake up, and the first words you say would be lost. So between dictations, Saywind keeps the microphone running but muted, using the per-app input mute built into macOS. While it’s muted, Saywind receives only silence: it hears nothing until you press the dictation key, and nothing is recorded or kept.

macOS shows the orange microphone indicator only while you dictate. Some third-party microphone monitoring apps may still list Saywind as using the microphone between dictations, because the microphone is running.

Saywind only does this with built-in microphones and ones connected by cable or USB, never Bluetooth. A wireless headset with a USB receiver counts as USB, so if you use one you may want to turn Instant start off. Saywind releases the microphone when your Mac sleeps, when the screen locks, and after 10 minutes without keyboard or mouse use. With Instant start off, Saywind uses the microphone only while you dictate.

What Saywind keeps, and where

Saywind stores these only on your Mac:

• Your dictation history.
• Your dictionary, replacements and settings.
• Recordings, only if you turn on “Keep recordings” in Settings. This is off by default.

Your dictionary and settings are kept in Saywind’s preferences on your Mac. Your history and any recordings are in ~/Library/Application Support/Saywind.

Learning your corrections

After Saywind pastes, it reads the text box you just dictated into for up to a minute. If you fix a misheard name there, Saywind learns it. This happens on your Mac only. You can switch it off in Settings.

Saywind needs Accessibility access for this, and to notice the dictation key and paste your text.

When Saywind uses the network

Saywind connects to the internet for two things only:

• Speech models: Saywind downloads each speech model from Hugging Face (huggingface.co) the first time it’s needed: the main model on first run (about 630 MB), a small word-spotting model (about 100 MB) the first time your dictionary has a word in it, and any other model you choose in Settings. Dictation itself works offline.
• Update check: at most once a day, Saywind fetches a small file from peiserapcar.com/saywind/latest.json to see whether there’s a newer version. The request carries no identifiers and no cookies, and nothing about you or your dictation is sent. You can turn this off in Saywind’s About tab.

As with any web request, the server that answers sees your internet (IP) address. Hugging Face’s own privacy policy covers its downloads. Our hosting providers may process request logs to deliver this website and protect their services.

How to delete your data

You can delete all history and recordings from Saywind’s History tab. Or quit Saywind, then delete the folder ~/Library/Application Support/Saywind. Moving Saywind to the Bin doesn’t remove this folder.

To remove your dictionary and settings too, quit Saywind and run defaults delete com.peiserapcar.saywind in Terminal.

The speech models (several hundred MB) are in ~/Library/Application Support/FluidAudio/Models. Delete that folder to free the space. Other apps built on FluidAudio may use the same folder.

Your rights

Saywind sends us nothing about you or your dictation. Under UK and EU data protection law, you can ask us for a copy of any personal data we hold about you, and ask us to correct or delete it. If you’re unhappy with how we’ve handled your data, you can complain to the Information Commissioner’s Office (ico.org.uk) or to the data protection authority where you live.

Changes

If this policy changes, the new version will be on this page with a new date.

Who we are

Saywind is published by Peiser Apcar LTD. Registered in England and Wales. Company number 16157036. Registered office: 8 Hestercombe Avenue, London, SW6 5LD.