Getting started
Just bought? Thank you. Here’s what happens next
Your key comes in a separate email from Piotr Januszek, not in the Lemon Squeezy receipt — by hand, usually within a day; there’s no activation server, which is also why the key is checked on your Mac. Use the trial meanwhile. If the trial has already ended: Settings ▸ App & Updates ▸ Licence ▸ “I’ve paid — waiting for my key”, with the order number from your Lemon Squeezy receipt, gives 7 days of full access, once per Mac. Nothing after 24 hours? Check spam, then email support@saykeep.app with your order number. Don’t buy again.
When it arrives, paste it into Settings ▸ App & Updates ▸ Licence.
Not on your Mac yet? The trial and the app you bought are the same download:
Saykeep installs on a Mac — send yourself the link
Just downloaded? Here’s what happens next, step by step.
Install
Open Saykeep-0.4.3.dmg, drag Saykeep into Applications and open it from there. It’s signed with an Apple Developer ID and notarized by Apple, so macOS opens it after one standard confirmation.
Three permissions, plus two questions
Each one, and when it comes up:
First run downloads the speech models
About 4.7 GB, once, with a progress bar, so the first run needs a connection for as long as your line takes; have about 5 GB free. Saykeep transcribes on this Mac and sends your audio nowhere; every connection it can make is on saykeep.app/network.
Say something
Hold your push-to-talk key (right Option, unless you change it in Settings ▸ Dictation), speak, and let go. About a second later, once the model is warm, the text is on your clipboard, ready to paste. Switch on Settings ▸ Privacy & Storage ▸ Dictated text ▸ “Insert it where my cursor is” and Saykeep pastes it where you were typing. Until your key is in, your 30-day trial is running (all features, no card, no account); see it in Settings ▸ App & Updates ▸ Licence.
Record your first call
Click the menu-bar icon and press Start meeting before the call starts. The first time, a consent notice explains where everyone has to agree, and macOS asks for System Audio Recording and your Documents folder. Tell the others you’re recording. Press Stop meeting when you hang up. The transcript, with who said what, is made afterwards (about 35 minutes per meeting-hour with speaker labels on, on the M5 we measured) and lands in ~/Documents/Saykeep and in Recordings.
Turn on summaries (optional)
Summaries need a model you connect: a free one on your Mac (LM Studio or Ollama) or your own API key for an OpenAI-compatible service. In Settings ▸ Summaries & AI enter the Endpoint address, the model name and, if the service needs one, the API key, then press Test. ChatGPT Plus doesn’t include API access. Without a model you still get the full transcript with speaker labels; Summarize now in Recordings writes the summary later, once you connect one. Summaries and ChatGPT, in full →