Willow Voice, or dictation that stays on your PC
You searched for Willow Voice on Windows, so you want to talk instead of type, and you want it to work in every app you use. Willow does run on Windows. It also, by its own help centre's account, runs on cloud models: your voice goes to its servers to become text, you sign in to use it, and its help centre caps the free plan by the week. Deixis is the other way to get the same thing on Windows. Hold a key, speak, and the words are typed where your cursor is, with the recognition happening inside the app on your own PC. No audio leaves. No account. Free, for everything that runs on your machine. And it runs on your Mac and your phone too, with the same recognition on the device.
That is the whole difference in one paragraph, and the rest of this page is the detail. Willow's own privacy pages are unusually clear about what it collects, so we quote them rather than guess, and where Willow does something Deixis does not, more languages, a tool that drafts whole messages from a rough idea, an offline option on its paid plan, we say so first and plainly.
If what you want is dictation on Windows that is fast, private by construction rather than by policy, and free without a weekly cap, read on.
Why switch
What you gain, and what you give up
Why Deixis
- One tool, on every device you own. Windows, Mac, iPhone and Android, with the same on-device speech recognition on all four; your audio never leaves any of them. On the iPhone it is a keyboard: switch to it, hold the microphone key, speak, and the text lands in the field. On Android it is a floating microphone bubble that dictates into any app, and the phone records and transcribes meetings on the handset as they run. Willow's download page offers Mac, Windows and iPhone, and nothing for Android.
- Your voice never leaves your PC. 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 is sent there to become text. Deixis recognises speech inside the app on your own machine, under every setting, always. There is no cloud mode to opt out of, because there is none, and the offline dictation that Willow lists as a feature of its paid Individual Pro plan, without saying which platforms carry it, is simply how Deixis works, on the free plan, with the network cable pulled. The only thing a fresh install does on its own is check for updates, and that sends nothing but the request.
- No account, ever, for dictation. Willow's setup guide lists creating an account among its onboarding steps. Deixis never asks you to sign in for anything that runs on your PC: dictation, hands-free notes, screenshots, screen recording, meetings, the dictionary. The only time it asks for an email address is for the cloud extras, starting with the seven-day trial, and even then there is no card and no password.
- Free, with no weekly cap. Willow's free plan runs on its weaker model. Its help centre's plan chart caps it at 2,000 words a week and five minutes a recording, and even the pricing page, which calls dictation on that model unlimited, caps Scribe at 20 uses a week. Everything local in Deixis is free forever and unmetered: dictation, hands-free mode, both speech models, the dictionary and all five vocabulary packs, screen capture and annotation, screen recording, and meeting recording with transcription.
- It knows which field you are in without reading your screen. A commit message, a chat reply and a ticket are punctuated differently, and Deixis punctuates them differently because the name of the app and the field ride along with the words. Never the window title, never a screenshot, never the text on the page.
- Talk and point at the same time. Free mode lets you narrate for as long as you like while grabbing a screen region, picking a button on screen, or taking the text you have selected. What you said and what you pointed at come out as one note, ready to paste into a bug report or a handover. Willow dictates; it does not do this.
- Screenshots, screen recording and meetings with the people in them named, all in the same key. Freeze the screen, drag a region, add arrows, boxes, numbered steps or a pixelated patch over anything private, and save. Record the screen, pause it, and stop it with the same key. Record a meeting, your side and theirs, and get a transcript written on your PC with the people in it named: Deixis tells the remote voices apart, you give each one a name, and from then on it recognises that person in later meetings. The voiceprint behind that is a mathematical fingerprint that stays on your machine, is never uploaded, and can be deleted per person.
- Nothing about you goes out, and everything of yours stays as a file. Willow's privacy policy lists what it collects even in Private Mode: device type, operating system, app version, performance and diagnostic information, your words-per-minute rate and the number of words you dictated. Deixis sends nothing about you at all: no analytics, no crash reports, no usage counts. What it keeps, notes, transcripts, screenshots, recordings and settings, sits in one folder on your PC as ordinary files. Back it up, search it, uninstall Deixis tomorrow and it is all still there and still readable.
Where Willow Voice still wins
- Over a hundred languages. Willow's pages say it dictates in more than 100 languages and switches between them mid-sentence. Deixis ships English speech models only.
- It writes for you, not just what you say. Willow Scribe takes a rough description of what you want to say and turns it into polished prose in your voice. Deixis cleans up what you dictated: punctuation, structure and the transforms you ask for out loud, and it never turns your words into something you did not say.
- A memory of your writing style. The paid plan learns how you write over time and adapts to your tone. Deixis carries your vocabulary and your previous sentence in that field along with each request, not a profile of you.
- It can read the text around your cursor. Context Awareness, when you switch it on, reads small bits of on-screen text so that names and terms come out spelled the way they already are on the page. Deixis sends the name of the app and the field, never the text on your screen. That is deliberate, but it means Willow can catch a spelling Deixis will not.
- Compliance paperwork for regulated teams. Willow offers HIPAA support with signed agreements, an enforced privacy mode and zero-data-retention options on its top plans, Business and Enterprise. Deixis has been through no such assessment; it answers the question differently, by never sending audio anywhere.
- Team plans with a shared team dictionary and shared shortcuts. Deixis teams share links and seats, not vocabulary.
What you get
More than dictation. One key, and everything behind it.
Hold the key and press a letter: free mode, a grab, a meeting, a recording, a translation, your own buttons. All of it on your own device, all of it free, none of it behind an account.
Dictation, where your cursor is
Hold a key, speak, release. Clean, punctuated text lands in whatever has focus, on your PC, your Mac and your phone, with your clipboard handed back.
Free mode: talk and point
Narrate for as long as you like while you grab a region, pick a button on screen 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 every screen at the keypress, drag a region, add arrows, boxes, text and numbered steps, and pixelate what is private. Saved as a PNG that stays editable.
Screen recording, shared as a link
Record the screen with your narration. The recording writes itself up with a title, chapters and a summary, and from your Deixis account it shares as a link anyone can open without one. The Loom you can stop paying for.
Meetings, no bot, names included
Your microphone and the other side, transcribed on your machine while the call runs. Deixis tells the voices apart and remembers the ones you name, and never uploads a voice.
Your own buttons and workflows
Add a button to the palette: it gets the note on stdin and types back whatever it prints. Send finished notes to any URL you own. Chain steps: read the text off a screenshot, translate it, summarise it, post it.
Side by side
Willow Voice and Deixis, side by side
| Row | Deixis | Willow Voice |
|---|---|---|
| Runs on | Windows 10 and 11 (any 64-bit PC from 2013 on), Mac (Apple Silicon), iPhone (as a keyboard) and Android (a dictation bubble in any app, plus meetings). One engine on all four, and 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 local, meetings included. Pro is $49 a year for the cloud extras with nothing to set up. | 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 | Add your own buttons that run a script, send finished notes to any URL you own, and switch on vocabulary packs for your field. | 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 5 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 onboarding steps, and its plans page says one account carries across Mac, Windows and iOS when you sign in with the same email. 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 PCapi.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 trialthe 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 | The finished note, and for a screenshot its file name, never the imagea URL you added yourself · on finish, only for destinations you added | 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; Deixis's speech models are English models, and Willow's hundred-plus languages are the reason to stay. If your PC is older than 2013 it will not run Deixis at all, and if your desk is a Linux box, Deixis is not there. If Willow Scribe has become how you write, drafting whole messages from a rough idea, Deixis cleans up dictation rather than composing it. And if your organisation needs a signed compliance 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.
The dictation key
Willow has a hotkey you press to dictate. Deixis has one gesture: hold Ctrl+Win, speak, release,
and the text lands at your cursor with the clipboard put back the way you left it. Double-tap the
same key instead and it keeps listening until you double-tap again, for the paragraph you have not
finished thinking yet. You can change the key in Settings if another one suits your hands better.
The first run
Willow signs you in. Deixis shows one Download button. Press it, wait for a file about the size of a short video, and you are dictating. That is the speech model, fetched once and kept on your PC. Settings offers a second, larger model that is more accurate and slower to decode, and it swaps in without a restart.
Your dictionary
Where Willow has a personal dictionary that learns names and terms, Deixis has a dictionary you can
add to without leaving what you are doing: select a word anywhere, press Ctrl+Win+D, done. Five
vocabulary packs ship in the box, for software, finance, business, medicine and law, and switching
one on takes a click. A word it keeps mishearing can be corrected once and fixed forever.
Private Mode, and what replaces it
Willow's Private Mode, which its security page calls Privacy Mode, decides what its servers keep. In Deixis the question is different, because nothing is sent to be kept: the only setting that matters is whether AI cleanup uses the network, and it is one choice in Settings → Cleanup. Out of the box, Deixis tidies your dictation on your PC with no provider and no key. If you want a language model to polish your sentences, choose between Deixis's cloud, a model running on your own machine, or your own key. Whichever you pick, the page linked at the bottom of this one says exactly what each choice sends, and you also choose how often: only when the local rules are not enough, every time, or never.
Transcript history
Willow keeps its transcript history on your device and warns that a new device starts empty. Deixis keeps yours the same way, in the Library, and as files in one folder you can copy anywhere.
Meetings, screenshots, recordings
Ctrl+Win+M records a meeting, both your voice and theirs, and transcribes it on your PC. The
remote voices come out told apart, and you name them: give each voice a name once, and the next
time that person is in a meeting Deixis recognises them and labels them. The voiceprint it uses is a
mathematical fingerprint that stays on your machine, is never uploaded, and can be deleted per
person. Ctrl+Win+S grabs and annotates a screenshot. Ctrl+Win+V records the screen to a video
file. All of it lands in one folder as files you can open with anything.
Before you ask
Questions people search for
Does Willow Voice work on Windows?
Yes. Willow's download page offers a Windows installer alongside the Mac and iPhone versions, and its help centre walks through the Windows setup. What its pages also say is that it uses cloud models: your audio goes to its servers to become text. Deixis is the Windows tool that does the recognition on your own PC instead, and needs no account to do it; it runs on the Mac and on your phone the same way.
Is Willow Voice free?
There is a free plan on Willow's weaker speech model, with weekly caps (the pricing page mentions 20 Scribe uses a week, and the help centre 2,000 words a week and five minutes per recording), and the Individual Pro plan was $15 a month, or $12 a month billed annually, when we checked. Deixis is free forever for everything on your PC, with no cap and no account. Pro, at $49 a year or $10 a month, adds the managed cloud extras with nothing to set up.
Does Deixis support a hundred languages like Willow?
No. Deixis dictates in English; its speech models are English models. If you dictate in another language, Willow is the better choice today, and this page will say so for as long as that is true.
Does Willow Voice work offline?
Willow's help centre lists offline dictation as a feature of its paid Individual Pro plan, and its home page mentions an offline mode, without saying which platforms have it. The free plan is cloud-based. Deixis works offline on every plan and in every mode, because the speech recognition never used the network in the first place.
Is Willow Voice private?
By its own pages, more careful than most: Private Mode is on by default, no dictated text is collected in it, and no audio is stored after transcription. But the audio still travels to Willow's cloud to be transcribed, and its policy still collects device, usage and diagnostic information. Deixis does not store your audio because it never receives it: recognition happens inside the app on your PC, and there is no telemetry of any kind.
Does Deixis upload my audio?
Never, under any setting. Speech recognition happens inside the app on your PC, and on your Mac and your phone it happens on the device the same way. The only things that can ever leave are text, and only once you switch a cloud feature on. The full list, every byte, is one page long and linked at the bottom of this one.
Hold a key. Speak. Keep working.
Deixis is free, needs no account, and runs on your own PC. Everything on this page is in the current release.
v0.9.0 · 64‑bit Windows 10/11 · 46.7 MB · nothing else to install
Facts about Willow Voice checked on 2026-09-05 against willowvoice.com. Deixis facts are from its README for the current release. Something out of date? Tell us.