Support

Most questions have a quick answer below. If yours does not, a human reads every message sent to the address at the bottom of this page.

Getting set up

Tulpa runs on Macs with Apple silicon or Intel, running macOS 13.4 or later. Apple Speech and Apple Intelligence cleanup need an Apple silicon Mac. Tulpa lives in the menu bar, so after setup its icon appears there rather than a window. If it will not open at all, check your macOS version under Apple menu, About This Mac.

It needs two permissions on macOS. Microphone, so it can hear you, and Accessibility, so it can type into whatever app you are using. Both are requested during onboarding; you can review them later in System Settings under Privacy and Security.

If dictation seems to do nothing at all, Accessibility is almost always the reason. macOS blocks the typing step while transcription itself keeps working, so the app looks like it heard you and then did nothing. If no text field is selected, Tulpa copies your words to the clipboard instead and says so.

Shortcuts stopped working

Usually this is macOS Secure Input. While a password field is focused, or an app has switched on secure keyboard entry, macOS hides keystrokes from every other app, so your Tulpa shortcut never arrives. Tulpa shows a warning and names the app when it can tell which one.

To clear it, finish or close any password or login prompt, then quit and reopen the app Tulpa named (password managers can hold it after you unlock them). In Terminal or iTerm2, turn off Secure Keyboard Entry in the app's menu. If no app is named, lock your Mac and unlock it again; if the warning stays, log out and back in.

If pressing fn opens emoji or starts Apple's dictation, macOS is using the key too. Open System Settings, Keyboard, and set Press 🌐 key to Do Nothing, so fn belongs to Tulpa alone.

Words are missing or slow

The speech model accounts for most of this. Parakeet Unified EN, the default, is English only and returns text as you speak; the multilingual models transcribe once you stop speaking, so text arrives a beat later, and cleanup adds a moment more if it is on. Switch models in Tulpa's settings.

Accuracy also depends on input level. If your microphone records quietly, quiet syllables are harder for any model to resolve, so raising the input gain in System Settings often helps more than changing models.

Working offline

Dictation does not need a connection. Once a speech model has been downloaded, transcription runs entirely on your machine, so planes, trains and dead-signal basements are fine.

The network is used to download models, check for updates, sign in and check your subscription if you have an account, and run the optional cleanup pass if you switch it on with a cloud provider.

Privacy and what leaves your machine

Audio never leaves your device, and Tulpa 1.0 does not save it. There is no setting that uploads it and no path in the app that sends it anywhere. History keeps recent transcript text on your Mac, and you can clear it.

From your dictation, the only thing that can ever be sent is text, for the optional cleanup pass, and only if you switch it on with a model that is not on your Mac. Cleanup is off by default, and cleanup with Apple Intelligence, on Apple silicon Macs, stays on your Mac.

Before you connect a cloud model of your own, Tulpa warns you that the text you send goes straight from your Mac to that provider, under its own terms, and asks you to confirm. On a Team plan, cleanup text goes from your Mac through our server to your team's provider, and we keep usage counts, never the text. Security has the full picture.

Teams and admin

Setting up a team. Create your team at account.tulpatalk.com, subscribe to Team ($12 per seat per month, seats include you), and invite people by email. An invited seat counts towards the bill until you remove it. Each person installs Tulpa, signs in with the same email, and has the Team plan.

Team cleanup. The admin can set one cleanup provider (address, model and API key) for everyone. The key is stored encrypted on our server and never sent to any Mac. Members get the same 7 day free trial per Mac as Solo.

Questions about Teams are welcome at hello@tulpatalk.com.

Billing and trials

Every Mac gets a 7 day free trial, with no card and no account needed to start dictating. When it ends, dictation stops until you subscribe. Solo is $8 a month or $69 a year, and Team is $12 per seat per month. Words are unlimited, because transcription runs locally and has no per-word cost.

To subscribe, use Buy in the app or go to account.tulpatalk.com, and sign in with the 6 digit code we email you. There are no passwords. Use the email you will sign in to Tulpa with, because your purchase unlocks that address.

Stripe, through Link, sells the subscription. It takes the payment, adds any sales tax or VAT, sends your receipt, and handles payment questions and disputes. Your card statement shows LINK.COM.

Refunds and cancelling. You can ask for a refund within 48 hours of a purchase or renewal charge, by writing to us or through Link. After 48 hours there are no refunds. To cancel, use Manage billing on the account page or Link's website: it stops all future billing, and you keep access to the end of the period you paid for.

Still stuck?

Email hello@tulpatalk.com. It helps to include your operating system version, the model you are using, and what you expected to happen versus what did.

Please do not send us your dictation. We do not need a recording or a transcript to help, and we would rather not receive one. Describing the problem is enough.