The Superwhisper alternative for Windows

Published 5 September 2026 · updated 14 October 2026

On a Mac? Superwhisper or Deixis on your Mac: the models, the price and what leaves

Superwhisper does run on Windows now, so this page is not about whether you can have it; it is about whether you should. Superwhisper's own Windows docs list what has not arrived there yet. Deixis was built for Windows first: every feature on this page is in the release you download today, and nothing about it is a port. It runs on your Mac and your phone as well, with the same on-device speech recognition, so one tool across your devices is not a reason to look elsewhere.

Hold a key, say the sentence, let go, and the text lands where your cursor was, with your clipboard put back. Deixis already knows which app and which field the words are going into, so a terminal command and an email come out punctuated differently, without a mode to build. It tidies your dictation on your PC with no key, no provider and no account. On Superwhisper the AI modes that do the tidying need Pro, and so does every language model that runs them, the one on your own PC included.

Superwhisper is a polished product with real strengths, a hundred-plus languages and custom modes over frontier models among them, and this page says so plainly below. But if your machine is a Windows PC, you want it to work today, and you would rather not sign up, paste a key or count words, Deixis is the better choice, and here is why.

Why switch

What you gain, and what you give up

Why Deixis

Whole on Windows, not its newest port. Windows is where Deixis was built. Superwhisper's Windows docs list settings sync, a custom app folder, hold-Shift-to-send, simulated keypresses, and its coding-agent integrations and command line as not yet available on Windows. Every feature on this page ships in the Deixis build you download, for any Windows 10 or 11 PC with an Intel or AMD processor with AVX2, from 2013 on, with nothing else to install. The same on-device speech recognition runs on Deixis's Mac and phone versions too, so your dictation audio never leaves any of them.
Cleanup that needs no Pro. Out of the box Deixis tidies your dictation on your PC with rules: no key, no server, no account, no word counter. On Superwhisper every AI mode runs on a language model, and every language model is a Pro feature at $8.49 a month: the default, S1-Language, runs in the cloud, and the one that runs on your PC, S1-mini, is on Pro as well.
What cleanup sends is deliberately small. When Deixis escalates a sentence to a language model, it sends the transcript, your vocabulary and the names of the app and the field, never the window title. Superwhisper's Super Mode sends the active window's title and name, the text in the input field, your selection, recent clipboard text, and your full name and computer name to the language model's provider. Its docs show you the prompt in History so you can check; Deixis would rather there be less to check.
The dictionary is one keystroke away, with packs in the box. Select a word anywhere and press Ctrl+Win+D and it is in your vocabulary; five vocabulary packs for software, finance, business, medicine and law switch on with a click. Superwhisper's free plan has vocabulary and replacements too, and its docs warn that too many words can confuse the transcription model; Deixis measures that limit for you, says in the dictionary when you are past it, and puts no limit on fixes.
Screenshots, screen recording, and talking while you point, in the same key. Freeze the screen, drag a region, add arrows, boxes, numbered steps or a pixelated patch over a secret, and save; every grab stays re-editable. Record the screen with your voice over it, with nothing to install. Or open a free session and narrate for as long as you like while grabbing a region, picking a button on screen or taking the text you have selected, and what you said and what you pointed at come out as one note, ready to paste into a bug report. Superwhisper is a dictation tool and does none of this.
Meetings with the voices told apart, free. One chord records your microphone and the system audio and transcribes both on your PC. Deixis tells the remote voices apart, and once you have named a voice it recognises that person in later meetings; the voiceprint is a mathematical fingerprint that stays on your machine, is never uploaded, and can be deleted per person. On Superwhisper, recording the system audio and separating the speakers are both on Pro.
A lower yearly price for the cloud tier, and your own key is free. Deixis Pro is $49 a year against Superwhisper's $84.99 (by the month, $10 against $8.49), and the trial is seven days you start yourself, by email code, with no card. Bring your own key instead and every cloud feature runs against it, free forever, with the key forwarded for that one call and never stored; on Superwhisper, using your own AI keys is on the Pro list. Nothing local is ever on a trial or behind a licence key.
Everything is a file, and your own buttons can act on it. Notes, transcripts, screenshots and settings sit in one folder as ordinary files. Add a button that posts a finished note to a URL you own or hands it to a script you wrote, and its output can be typed back where you were. Deixis ships that on Windows today.

Where Superwhisper still wins

Both phone apps are in the stores, on one licence. Superwhisper's iPhone and Android apps are in the App Store and on Google Play, and one Pro licence covers them along with unlimited Macs and Windows PCs. Deixis is on Google Play too, but its iPhone keyboard is still in beta on TestFlight.
Windows on ARM. Its Windows docs say it runs on Windows 10 and 11 on x64 and ARM64 processors, with Parakeet or a cloud model as the speech model on ARM. Deixis needs an Intel or AMD processor with AVX2 and has no build for Windows on ARM, so on a Snapdragon laptop Superwhisper is the one of the two that runs.
A hundred-plus languages. Superwhisper transcribes in over a hundred languages and dialects, detects the language automatically, and on Pro translates any of them into English. Deixis dictates in English: its speech models are English models.
Files in. Drop in an MP3, a WAV or an MP4 and get a transcript. Deixis transcribes only what it records, live dictation, meetings and screen recordings, and does not take a file you made elsewhere.
Custom modes over a menu of language models. Write exactly how a mode should think, write and format, choose which context it sees, and run it on Claude, GPT, a Groq-hosted model, Superwhisper's own in the cloud, or its S1-mini on your own PC, all on Pro, with your own keys for the cloud ones if you like. Deixis adapts to the field automatically, has no per-mode prompt for you to write, and keeps the provider choice to one clear setting.
Words while you speak. On Pro, realtime transcription shows your words on screen as you talk, with a local Parakeet model or a cloud one. Deixis types the text when you let go of the key.
Enterprise controls. Single sign-on, silent rollout through Jamf, Intune or any device manager, model access control, and security certifications it names on its site. Deixis has teams, seats and a switch that turns the cloud off for everyone in a team, but no single sign-on and no managed rollout.
A shelf of local speech models. Every Whisper model, from 75 MB to 3 GB, is free on Superwhisper, and Pro adds Cohere Transcribe and Nvidia's Parakeet. Deixis ships two English models and no more.

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.

The Deixis panel tethered to the caret in a code editor, listening — 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.

A finished free-mode note with two captured references interleaved with the narration — 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.

A frozen screen with a dashed selection, numbered steps, an arrow and a pixelated patch — 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.

The page Deixis writes for a shared recording: a short link, a title, a summary and the video — 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.

A meeting transcript with timestamps and named speakers, and a level meter — 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.

A custom button definition, a webhook delivery and the vocabulary packs — 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

Superwhisper and Deixis, side by side

Row	Deixis	Superwhisper
Runs on	Windows 10 and 11 (64-bit, on an Intel or AMD processor with AVX2: 2013 and later; no build for Windows on ARM), Mac (Apple Silicon) and Android (a dictation bubble in any app, plus meetings), with an iPhone keyboard in beta on TestFlight and not yet in the App Store. Meetings run on Windows and Android. One engine on all of them, and dictation audio never leaves the device.	macOS, Windows 10 and 11, on x64 and ARM64, iOS, Android
Speech recognition happens	On your own device, inside the app, on every platform. Dictation audio never leaves it; a meeting's, only if you turn on cloud processing on Android.	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.	On your device or in the cloud, your choice
Leaves your machine	Text, and only once you switch a cloud feature on, plus, on Windows, one key you press to check your own Claude plan, and, on Android, a meeting's audio if you turn on cloud processing for meetings. Never a dictation's audio, never screenshots, never window titles.	Audio, text, window titles
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.	not documented
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 that does not expire: unlimited dictation on any local Whisper model, custom vocabulary, text replacements and up to two modes, plus 3,000 words of Pro to try; $249.99 one-time; $8.49 a month; $84.99 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.	Custom modes with your own AI instructions and a choice of which context each one sees; your own AI keys on Pro; one Pro licence across unlimited Macs and Windows PCs plus an iPhone and an Android phone; a command line and an MCP server over your dictation history; enterprise single sign-on, rollout through Jamf or Intune, and model access control

Superwhisper facts from superwhisper.com, its privacy policy, its docs, its Windows page, its Windows docs, its Pro docs, its voice-model docs, its language-model docs, its security docs, its compliance docs, its account docs, its Super Mode docs, its custom-mode docs, its meeting docs, its file-transcription docs, its context docs, its enterprise docs, its analytics docs, its history docs, its vocabulary docs, its quickstart docs and its CLI and MCP announcement, read on 7 October 2026. “Not documented” means those pages did not say.

What Superwhisper sends depends on the models you pick. On the free plan, which runs on its local Whisper models, its plans page says nothing you dictate leaves your device. Its AI modes and cloud voice models are Pro, and all of them run in the cloud except one language model, S1-mini, which runs on your own machine; its Super Mode sends the window title along with the text.

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 Superwhisper's own pages say.

What	Deixis	Superwhisper
Audio	A dictation's, never: recognition happens inside the app on your device, and the recording, the model and the transcript stay there. A meeting's, only if you turn on Deixis cloud processing for meetings on Android: its audio, in pieces, each its own request, and Deixis stores and logs none of itapi.deixis-voice.com, then Whisper on Cloudflare Workers AI · only on Android, after a meeting ends, with cloud processing switched on in Settings › Meetings — on Wi-Fi, or on mobile data only if you choose	Nothing with a local voice model: the local Whisper models run on the device and the privacy policy says no audio is collected. With a cloud voice model — Superwhisper's own servers or Deepgram, all Pro — the audio goes out for transcription; its security docs say those providers keep nothing and do not train on it.Superwhisper's servers or Deepgram · only with a cloud voice model selected
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 transcript, whenever an AI mode runs on a cloud language model: Superwhisper's own S1-Language by default, or an Anthropic, OpenAI or Groq model, all of them Pro. Its one local language model, S1-mini, also Pro, keeps the text on the device on macOS and Windows.the provider of the language model you picked · on every dictation in an AI mode with a cloud language model
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	The active window's title and name, text from the active input field, selected text and recently copied text, plus the date, time, your full name and computer name. History shows the full prompt that went, so you can check.the provider of the language model you picked · in Super Mode, and in any mode with a context source on
Telemetry and analytics	None. No account, no telemetry, no analytics, no crash reports.	None, says the privacy policy: no usage data is collected. An enterprise dashboard, off by default until an owner turns it on, counts dictations, mode, model, duration, app version and platform — never audio or text.the vendor, enterprise plans only · only when an enterprise owner switches it on
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	A model download when you pick a local model: the Whisper models, 75 MB to 3 GB, are free; Cohere Transcribe (1.3 GB) and the Parakeet models (about 480 MB) are Pro. The docs do not say what the request carries.not stated · when you select a model
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	A licence key for Pro, emailed at purchase and pasted into the app. The vendor holds your account's email address and billing records and says it never stores transcripts or audio; on deletion the address is obfuscated and the billing records kept in anonymised form.the vendor and its payment processor · on purchase and activation
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	Your modes, vocabulary and settings, if you turn on FileSync, which syncs configuration between your Macs through Superwhisper's servers; its docs say it never stores transcripts or audio.Superwhisper's servers · only with FileSync on

The same table for every tool we have measured

Before you switch

Who should not switch

If you dictate in a language other than English, wait: Deixis's speech models are English models. If you need a tool that takes an audio or video file, Superwhisper does and Deixis does not. If your company needs single sign-on and silent deployment, that is Superwhisper's enterprise tier. If your PC is a Windows on ARM machine, such as a Snapdragon laptop, Superwhisper runs on it and Deixis has no build for it. There is no Linux build. And if your PC is older than 2013, its processor lacks the AVX2 instructions Deixis's speech engine is built on, and the app will stop rather than run slowly.

Making the switch

Five minutes from installed to dictating. Here is what maps to what.

Dictation

Superwhisper's recording shortcut becomes the one gesture Deixis is built around: hold Ctrl+Win, speak, release, and the text lands at your cursor with your clipboard restored. Change the chord in Settings if another suits your hands better. Double-tap it instead for hands-free mode, which keeps listening until you double-tap again and then pastes the whole note at once. There is no separate push-to-talk to enable; holding the key is push-to-talk.

The speech model

Superwhisper's voice-model page lists a catalogue to choose from: every local Whisper model, 75 MB to 3 GB, is free, with Cohere Transcribe, Parakeet and the cloud models on Pro. Deixis shows one Download button on first launch: press it, wait for a file about the size of a short video, and you are dictating. Settings offers a second, larger model that is more accurate and slower to decode, and it swaps in without a restart. Both are included, both are free, and there is no licence tier between you and either of them.

Your words

Superwhisper's Vocabulary sends hint words along with your audio and its Replacements rewrite the result afterwards. Deixis has the same two halves in one free dictionary: vocabulary that biases the speech recognition itself, and fixes that rewrite a word it keeps mishearing, once and forever. Add a word without leaving what you are doing: select it and press Ctrl+Win+D. Five vocabulary packs ship in the box and switch on with a click; drop in your own beside them if you have one.

AI cleanup

Superwhisper's modes become one setting in Deixis, Settings → Cleanup, with three positions: When it helps, Every time, and Never. When it helps is the default: rules on your PC handle most sentences, and only a request like "make this a bullet list" or a long unpunctuated stretch goes to a language model, if you have set one up. Every time sends each sentence for better prose and accepts the short wait. Never keeps dictation off the network entirely. Where the language model runs is your choice too: Deixis's cloud with nothing to set up, a model on your own machine through Ollama, or your own key. Whichever you pick, the byte table linked at the bottom of this page says in plain words what each choice sends. Super Mode's job, matching the format to the app you are in, is what Deixis does by default, from the app and field names alone.

Meetings, screenshots, recordings

Ctrl+Win+M records a meeting, both your voice and theirs, and transcribes it on your PC into a readable transcript with the people in it named: Deixis tells the remote voices apart, and once you have named a voice it recognises that person in later meetings, with a voiceprint that stays on your machine, is never uploaded and can be deleted per person. Notes and action items follow if you have a cleanup endpoint set. S freezes the screen for a grab you can annotate. V records the screen with your narration. T translates whatever you have selected. All of it lands in one folder as files you can open with anything.

Before you ask

Questions people search for

Does Superwhisper work on Windows?

Yes. Superwhisper's Windows page offers a download for Windows 10 and 11, with a free tier that does not expire. Its Windows docs list several features that have not reached Windows yet. Deixis was built for Windows, every feature on this page ships in the build you download, and it runs on the Mac and the phone as well.

Is Superwhisper's Windows version the same as on macOS?

Not yet, by its own account. Its Windows docs list settings sync, a custom app folder, hold-Shift-to-send, simulated keypresses, and its coding-agent integrations and command line as not available on Windows yet, with settings sync still in development. Deixis on Windows has nothing waiting on another platform: Windows is where it was built, and the Mac and phone versions followed it, not the other way round.

Is Deixis free?

Yes, for everything that runs on your own device, forever, with no account and no licence key: dictation, hands-free notes, meeting recording and transcription, screenshots, screen recording, the dictionary and all five vocabulary packs. Pro, at $49 a year or $10 a month, adds the managed cloud extras; your own key makes those free too.

Does Deixis need an account or a licence key?

No. Nothing that runs on your own device ever asks you to sign in, and there is no key to paste. The only time Deixis asks for an email address is when you choose a cloud extra, such as starting the seven-day trial, and what comes back is a six-digit code, not a password or a card.

What does Deixis send to the cloud compared with Superwhisper?

Never the audio of a dictation, under any setting, and a meeting's only if you turn on Deixis cloud processing for meetings on Android: speech recognition happens inside the app on your device, on Windows, Mac and Android alike and in the iPhone keyboard now in beta, and the voiceprints meeting mode keeps to tell speakers apart never leave the machine either. With a cloud cleanup endpoint set, Deixis sends the sentence, your vocabulary and the names of the app and the field, never the window title. Superwhisper's cloud voice models receive the audio, its AI modes on a cloud language model receive the transcript, and Super Mode adds the window title, input field text, selection, clipboard and your name. The full Deixis list, every byte, is one page long and linked at the bottom.

Can I use my own provider key with Deixis?

Yes, and it costs nothing: every cloud feature runs against your own key if you set one, an OpenRouter key being the one the documentation walks through, and Deixis never stores it. Or run a model on your own machine through Ollama and keep everything local. On Superwhisper, bringing your own key is itself a Pro feature.

Keep reading

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.

Download Deixis for Windows or Mac Every byte that leaves

v1.3.2 · 64‑bit Windows 10/11 on Intel or AMD · macOS 13 on Apple silicon · 51 MB · nothing else to install · Android on Google Play

Facts about Superwhisper checked on 7 October 2026 against superwhisper.com. Deixis facts are from its documentation for the current release. Something out of date? Tell us.

The Superwhisper alternative for Windows