Willow Voice, or the same hotkey with the cloud left out
If you are weighing up Willow Voice on your Mac, you want what Deixis is built for: press a key,
talk, and have finished text appear wherever you were typing. Deixis does it with the speech
recognition running on your Mac, on Apple Silicon, on the free plan, with no account. Hold
Ctrl+Option, speak, release, and the words land at the cursor in whatever app has focus, with your
clipboard handed back.
Willow made the opposite bet and says so plainly. Its help centre says it uses cloud-based AI models, because on-device models cannot match their performance right now, and lists offline dictation as a feature of the paid Individual Pro plan. Its Mac install guide has you create an account before you dictate, and its free plan runs on what its own pricing page calls the weaker model.
Willow's privacy pages are among the more careful in the category, and where it does something Deixis does not, more languages, drafting from a rough idea, a finished iPhone app, this page says so first. But if you would rather your Mac did the listening, for nothing, here is the case.
Why switch
What you gain, and what you give up
Why Deixis
- On-device by default, and free. Willow's help centre says it uses cloud-based AI models, and its security page says it runs on cloud infrastructure in the United States: your audio goes there to become text. Offline dictation is a feature of the paid Individual Pro plan, and the help centre does not say which platforms carry it. In Deixis, on-device is not a plan or a mode. The recognition runs on your Mac under every setting, on the free plan, and it keeps dictating with the Wi-Fi off.
- No account, ever, to dictate. Willow's Mac install guide lists creating an account among its onboarding steps, ahead of microphone and Accessibility access. Deixis never asks you to sign in for anything that runs on your Mac. An email address comes into it only if you choose to start the seven-day trial of cloud cleanup, and even then there is no card and no password.
- No weekly cap. Willow's free plan runs on Frontier Mini, which its pricing page calls the weaker model, and caps Scribe at 20 uses a week; its help centre's plan chart caps the free plan at 2,000 words a week. Individual Pro is $15 a month, or $12 a month billed yearly. Everything local in Deixis is free and unmetered, and Pro, at $49 a year, is cloud cleanup with nothing to set up.
- Nothing about you goes out. Willow's privacy policy says that even in Private Mode it collects technical and operational information, and lists it: device type, operating system, app version, performance and diagnostic information, your words-per-minute rate and the number of words you dictate. Deixis sends none of that. No telemetry, no analytics, no crash reports, no usage counts.
- It knows the field without reading the screen. A chat reply, an email and a document are punctuated differently, and Deixis punctuates them differently because the names of the app and the field go along with your words when cloud cleanup is on. Never the window title, never the text on the page, never a screenshot.
- Free mode, grabs and screen recording on the same chord. Double-tap
Ctrl+Optionand talk for as long as you like while you grab a region or take a selection; you get one note back with what you said and what you pointed at, in order, pasted where you finish.Ctrl+Option+Sfreezes the screen for a grab you can mark up with arrows, boxes, text and numbered steps, or pixelate.Ctrl+Option+Vrecords the screen to a video, narrated when a microphone is set up for it. Willow's product pages list dictation, Scribe and the iPhone app, and none of these. - Your history is plain files. Willow's help centre says transcript history lives only on the device, so a new one starts empty. Deixis keeps its history on your Mac too, but with your notes, grabs and recordings as ordinary files in one folder: back it up, search it, open it with anything, and uninstall Deixis tomorrow without losing a word.
Where Willow Voice still wins
- Over a hundred languages. Its home page says Willow dictates in more than 100 languages and switches between them without missing a beat. Deixis ships English speech models only.
- It drafts, not just transcribes. Willow Scribe takes a rough description of what you want to say and writes it out in your voice. Deixis tidies what you actually said, punctuation, structure and the transforms you ask for, and never writes a sentence you did not dictate.
- It learns your style. The paid plan's smart memory learns how you write over time and adapts to your tone, its home and pricing pages say. Deixis carries your vocabulary and your previous sentence in that field along with a request, not a profile of you.
- It can read around the cursor. Context Awareness, which you switch on yourself, reads small bits of text around your cursor so that names come out spelled as they already are on the page, and the help centre says that text is not stored. Deixis sends the name of the app and the field, never what is on screen, which means Willow can catch a spelling Deixis will not.
- A finished iPhone app. Willow's iPhone app is in the App Store and shares one account with the Mac. Deixis's iPhone keyboard is a beta on TestFlight and not yet in the App Store.
- Paperwork for regulated teams. Its Business and Enterprise plans list HIPAA support, an enforced privacy mode, zero data retention and single sign-on, and the Team plan shares a dictionary and shortcuts. Deixis has been through no such assessment; it answers the question by not sending audio anywhere.
What you get
More than dictation, on your Mac.
Hold Ctrl+Option and speak, or press a letter while you hold it: free mode, a grab, a screen recording. All of it on your Mac, all of it free, none of it behind an account.
Dictation, where your cursor is
Hold Ctrl+Option, speak, release. Clean, punctuated text lands in whatever app has focus on your Mac, with your clipboard handed back.
Free mode: talk and point
Double-tap the chord and narrate for as long as you like while you grab a region or take a selection. One note, what you said interleaved with what you pointed at, pasted where you finish and saved as Markdown.
Screen grabs, annotated
Freeze the screen at the keypress, drag a region, add arrows, boxes, text and numbered steps, and pixelate what is private. Saved as a PNG in a folder you own.
Screen recording
Record the screen, pause when you need to, and stop. The video is a file in a folder on your Mac, not in somebody else's cloud.
Side by side
Willow Voice and Deixis, side by side
| Row | Deixis | Willow Voice |
|---|---|---|
| Runs on | Mac, on Apple Silicon with macOS 13 or later, and the same app on Windows 10 and 11 and on Android, with an iPhone keyboard in beta on TestFlight. One engine on all of them, and dictation audio never leaves the device. | macOS, Windows, iOS |
| Speech recognition happens | On your own device, inside the app, on every platform. Your audio never leaves it. | On your device or in the cloud, your choice |
| AI cleanup happens | On your device, with no provider at all. Or, if you want more, Deixis's cloud, your own Ollama, or your own key. Your choice, in one setting. | In the cloud |
| Leaves your machine | Text only, and only once you switch a cloud feature on. Never audio, never screenshots, never window titles. | Audio, text |
| Account needed | None, ever, for anything that runs on your device. The cloud extras have a seven-day trial you start with an email code. No card. | Required |
| Price | Free forever for everything that runs on your Mac. Pro is $49 a year for the cloud extras with nothing to set up; on a Mac, that is cloud cleanup. | Free tier: a free plan on the weaker Frontier Mini model; the pricing page calls dictation on it unlimited and caps Scribe at 20 uses a week, while the help centre's plan chart caps it at 2,000 words a week and five minutes per recording; $15 a month; $144 a year |
| Your transcripts live | In plain files, in one folder you own and can back up. Uninstall Deixis and every note is still readable. | On your device |
| Make it yours | Your own dictionary of the names and jargon you use, in its own window. Custom buttons and webhooks are on Windows today, not yet on the Mac. | A personal dictionary, shortcuts for phrases you use often, Willow Scribe for turning rough notes into prose, an optional read-only link to your Google calendar and contacts, and a shared team dictionary on the Team plan |
Willow Voice facts from home, willowvoice.com, its privacy policy, security, download, terms, install, help-privacy and help-plans, read on 27 September 2026. “Not documented” means those pages did not say.
Willow's help centre says it uses cloud-based AI models by default, and lists offline dictation as a feature of the paid Individual Pro plan without saying which platforms carry it; the rows above describe the default. Its install guide lists creating an account among the Mac onboarding steps, and its plans page says one account carries across Mac, Windows and iOS when you sign in with the same email and login method. Its download page lists Android, but not as a download yet. Context Awareness, which reads text around your cursor, is off until you switch it on. The help centre and privacy policy call the default Private Mode; the security page calls it Privacy Mode.
What leaves your machine, and what leaves theirs
Deixis publishes every byte it sends, as a table, because there is so little of it. Here is that table beside what Willow Voice's own pages say.
| What | Deixis | Willow Voice |
|---|---|---|
| Audio | Never. Recognition happens inside the app on your device; the recording, the model and the transcript stay there. | Your voice, to be turned into text: the help centre says Willow uses cloud-based AI models, and the security page says it runs on cloud infrastructure in the United States. The privacy policy says audio is processed transiently by Willow and its service providers, and the security page that no audio is stored after transcription. A copy stays on your device for re-transcription.Willow's cloud and its service providers · every dictation, unless you are on the paid plan's offline dictation |
| The dictated text | The sentence you just dictated, your vocabulary, and your previous sentence in that fieldthe endpoint you chose · only with a cloud endpoint set, and by default only when the local rules are not enough | The recognised text is produced in the cloud. In Private Mode, the default, the help centre says no dictated text is collected; if you switch on Help Willow Improve, anonymised recognised text is kept to train its correction models.Willow's cloud · every dictation |
| Context around the text | The names of the app and the field the text is going into. Never the window title, never a screenshot.the same endpoint · with that request | With Context Awareness switched on, relevant text from the active window, described as small bits of text around your cursor, to improve spelling and formatting; not retained. When it is off, the help centre says Willow does not read any on-screen text.Willow's cloud · only with Context Awareness on |
| Telemetry and analytics | None. No account, no telemetry, no analytics, no crash reports. | Device type, operating system, app version, performance and diagnostic information, your words-per-minute rate and the number of words dictatedWillow · not stated |
| Update check | Nothing but the request; the version check happens on your Macapi.deixis-voice.com · every launch, and when you ask in Settings | not documented |
| Model download | Nothing but the requesthuggingface.co · once, when you press Download on first run | not documented |
| Account and sign-in | An email address, only if you choose to start the trial, plus the partner tag from a partner download link and the first partner website that connected to Deixis on this computer, if there are anythe Deixis endpoint · when you start the trial | Name, email address, authentication information, account settings and subscription statusWillow · when you create the account and sign in |
| Integrations | Nothing: webhooks are on Windows today, not yet on the Mac | If you connect a Google account: calendar events, contacts and directory entries, read-only, fetched when needed and discarded after the requestGoogle, through Willow · only if you connect it |
Before you switch
Before you switch
Who should not switch
If you dictate in a language other than English, stay with Willow; its hundred-plus languages are the reason to. If Scribe has become how you write, drafting whole messages from a rough idea, Deixis cleans up dictation rather than composing it. If the iPhone matters as much as the Mac, Willow's app is finished and Deixis's is still a beta. Deixis needs an Apple Silicon Mac on macOS 13 or later. And if your organisation needs a signed agreement more than it needs the audio to stay on the machine, that paperwork is Willow's to offer, not ours.
Making the switch
Five minutes from installed to dictating. Here is what maps to what.
Installing
The same shape as Willow's: open the disk image, drag Deixis to Applications, and grant microphone and Accessibility access when macOS asks, which it does the first time you dictate; both live in System Settings → Privacy & Security. There is no account step after that. Updates arrive through the app, in Settings → Updates.
The key
Willow's home page tells you to press your hotkey and speak. Deixis's is Ctrl+Option: hold it,
speak, release. If you gave Willow the same chord, quit Willow while you try Deixis so that only one
app answers. Double-tap Ctrl+Option instead for free mode, which keeps listening until you
double-tap again, for the paragraph you have not finished thinking yet.
The speech model
Willow signs you in; Deixis shows one Download button. That is the speech model, fetched once and kept on your Mac. After it, the two calls a fresh install makes on its own are an update check at launch and, when you open the Settings window, a check for an announcement from us, and neither sends anything but the request.
Your dictionary
Deixis has no importer for Willow's personal dictionary, so bring the words over by hand. The Dictionary window takes the names and terms you want recognised and fixes for the ones Deixis keeps mishearing, and a fix, once made, applies every time.
Private Mode, and what replaces it
Willow's Private Mode, which its security page calls Privacy Mode, decides what its servers keep. Deixis has nothing like it because nothing reaches a server to be kept: the one setting that matters is whether cleanup uses the network, in Settings → Cleanup. Out of the box it tidies your dictation on the Mac with rules and no provider. For more polish, choose Deixis's cloud, a model on your own machine, or your own key, and choose how often: When it helps, which is the default, Every time, or Never.
Your Willow account
Your subscription is managed on Willow's side. Its transcript history stays on the Mac it was made on, per its help centre, so keep anything you need from it before you uninstall.
Before you ask
Questions people search for
Does Willow Voice work offline on a Mac?
Its home page lists an offline mode, and its help centre lists offline dictation as a feature of the paid Individual Pro plan, without saying which platforms carry it; by default Willow uses cloud models. Deixis works offline on every plan and in every mode, because the recognition never used the network in the first place.
Is Willow Voice free?
There is a free plan on the weaker Frontier Mini model, with weekly caps: its pricing page caps Scribe at 20 uses a week, and its help centre caps the plan at 2,000 words a week. Individual Pro is $15 a month, or $12 a month billed yearly. Deixis is free for everything that runs on your Mac, with no cap and no account; Pro, at $49 a year or $10 a month, is cloud cleanup with nothing to set up.
Is Willow Voice private?
By its own pages, more careful than most: Private Mode is on by default, no dictated text is kept in it, and its security page says no audio is stored after transcription. But the audio still travels to Willow's cloud to become text, and its privacy policy still collects device, diagnostic and usage information. Deixis does not store your audio because it never receives it.
Why does Willow use the cloud?
Its help centre says cloud models give better accuracy and speed than on-device models can today. That is a real argument, and Willow's hundred-plus languages are part of it. Deixis makes the other trade: English speech models that run on your Mac, so that privacy is a matter of where the work happens rather than of which setting you chose.
Does Deixis need an account on a Mac?
No. Dictation, free mode, screen grabs, screen recording, your history and your dictionary all work without signing in to anything. An account only comes into it for cloud cleanup run by us, and the seven-day trial of that starts with a code sent to your email, with no card.
Does Deixis upload my audio?
Never, under any setting. Speech recognition happens inside the app on your Mac. The only content that can leave it is text, for cloud cleanup, and only once you switch that on. The full list of what leaves, every byte, is one page long and linked at the bottom of this one.
Keep reading
Related pages
How to type by voice in any app on a Mac, with the speech recognised on the Mac itself
How to type by voice in any app on a Mac: hold Ctrl+Option, speak, let go. Speech recognition runs on your Mac, free and with no account.
Here is every byte that leaves your machine, for each tool
Every byte Deixis sends off your machine in one table, and the same table filled in for other dictation tools from their own documentation, dated.
Aqua Voice, or dictation that works with the Wi-Fi off
Aqua Voice says it has no offline mode and gives you 1,000 free words. Deixis recognises speech on your Mac itself, free, with no account and no meter.
MacWhisper transcribes your files. Deixis types where your cursor is.
MacWhisper is a transcription app first. Deixis is dictation first: hold Ctrl+Option on your Mac and clean text lands at the cursor, free, no account.
Superwhisper or Deixis on your Mac: the models, the price and what leaves
Superwhisper puts its AI modes and every language model on Pro. Deixis tidies your dictation on your Mac for free, and never sends your window title.
Wispr Flow, or dictation your Mac keeps to itself
Wispr Flow transcribes in the cloud and, on a Mac, can send a screenshot with each dictation. Deixis dictates on your Mac itself, free, with no account.
Hold a key. Speak. Keep working.
Deixis is free, needs no account, and runs on your own device. Everything on this page is in the current release.
v1.2.2 · 64‑bit Windows 10/11 · macOS 13 on Apple silicon · 51 MB · nothing else to install · also for Windows
Facts about Willow Voice checked on 2026-09-27 against willowvoice.com. Deixis facts are from its README for the current release. Something out of date? Tell us.