The Typeless alternative that never uploads your voice
Typeless makes a good pitch: talk in a mess, get clean writing, in any app. If you are on Windows and weighing it up, the part its home page does not lead with is in its privacy policy: your audio and the context around it are "processed in real time on our cloud servers", and you sign in with Google, Apple or an email address before the first sentence. The free plan is generous, 8,000 words a week, and then it is $30 a month or $12 a month billed yearly. Deixis does the same job with the recognition on your own PC, no account, and nothing metered.
Hold Ctrl+Win, speak, release. The text is typed at your cursor in whatever has focus, editor,
terminal, browser, chat, with the clipboard restored. Filler words are dropped and the sentence is
punctuated by rules on your machine; if you want a language model to do more, that is one setting,
and it can run on your PC too. Everything that runs locally is free for as long as you use it.
Typeless is ahead on languages and on the polish of its AI features, and this page says so below. Where it cannot compete is on where your voice goes, on your PC, your Mac or your phone, and for a lot of people that is the whole question.
Why switch
What you gain, and what you give up
Why Deixis
- Your voice never leaves your PC. Speech recognition happens inside the app, on your processor. Typeless's privacy policy says audio and contextual information are processed on its cloud servers and discarded once the result is returned. Discarded is better than kept; never sent is better than both. It also means Deixis works offline: with no cloud endpoint configured it dictates, records and transcribes meetings, and grabs screens with no connection at all, where Typeless's recognition is on its servers and needs one.
- 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, on Android a floating microphone bubble that dictates into any app, and everything that runs on the device is free there too, with no weekly allowance.
- No account, ever, for anything local. Typeless's setup guide has you sign in with Google, Apple or your email address. Deixis never asks. Install, download the speech model once, dictate. The only time it wants an email is if you choose to start the trial of the cloud extras, by a six-digit code, with no card and no password.
- No cap and no meter. Typeless's free plan stops at 8,000 words a week; unlimited is $30 a month or $12 a month billed yearly. Everything that runs on your PC in Deixis is free and uncounted: dictation, hands-free notes, the dictionary and all five vocabulary packs, screen grabs, screen recording and meetings. Pro is $49 a year for the managed cloud extras, and with your own provider key those cost nothing from Deixis either.
- Context that is a name, not your screen. Typeless's policy says it sends "the application you're using and relevant text within it" with your audio. Deixis is field-aware without that: what can leave is the transcript, your vocabulary, the name of the app and the field, and the last thing you dictated into that field; never the text already on your screen, never the window title, never a screenshot, and only once you have switched cloud cleanup on.
- Cleanup you choose, including none. Rules on your PC tidy every utterance with no provider and no key. Want more? One setting: Deixis's cloud, a model on your own machine, or your own key, and how often, When it helps, Every time, or Never. Typeless's policy says data goes to third-party LLM providers, under zero retention; in Deixis whether anything goes anywhere is your decision, not the default.
- Meetings that know who is talking, grabs and recording, on the same key.
Ctrl+Win+Mrecords a meeting, your microphone and the other side, and transcribes it on your PC as it runs. You name the people in it, and voice identification tells the remote voices apart; once you have named a voice, Deixis 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 Android, meetings are recorded from the phone's microphone and transcribed on the phone, with notes.Sfreezes the screen for a grab you can annotate.Vrecords the screen to a video, narrated when a microphone is set up for it. Typeless dictates. - Everything is a file you own, and a toolbar you can extend. Notes, transcripts, screenshots, recordings and settings sit in one folder as ordinary files. Back it up, search it, uninstall Deixis tomorrow and every word is still there. Add a button that runs your script or posts a finished note to a URL you own, and it appears on the toolbar beside the built-in ones.
Where Typeless still wins
- A hundred-plus languages, detected automatically. Its pricing page lists support for 100+ languages on every plan, the free one included, and its home page says it detects the language you are speaking on its own. Deixis ships English speech models.
- Translate and Ask anything, built in on the free plan. Its pricing page puts translation and an Ask-anything mode in the free tier. Deixis can translate a selection, but that needs a cloud endpoint, your own key, or a model on your own machine.
- A tone per app. Its home page describes different tones for each app you write in. Deixis adapts punctuation and structure to the app and field; it does not carry a tone setting per app.
- A bigger free allowance than most. 8,000 words a week is a lot of dictation for nothing. Deixis has no allowance to compare it with, because nothing local is metered, but if you were only ever going to use a cloud tool for free, Typeless's cap is a generous one.
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
Typeless and Deixis, side by side
| Row | Deixis | Typeless |
|---|---|---|
| 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. | Windows, macOS (Apple Silicon and Intel), iOS, Android |
| Speech recognition happens | On your own device, inside the app, on every platform. Your audio never leaves it. | In the cloud |
| 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: 8,000 words a week, standard accuracy; $30 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, translation, an Ask anything mode and a tone per app, per its pricing and home pages. Its pages document no scripting, buttons or webhooks. |
Typeless facts from typeless.com, its privacy policy, home, setup and faq, read on 5 September 2026. “Not documented” means those pages did not say.
Typeless recognises speech on its own cloud servers: its privacy policy says audio and contextual information are processed there in real time and discarded once the result is returned to your device, and that text sent to third-party LLM providers is configured for zero retention with them. Dictation history stays on the device unless you enable History cloud sync; the pricing page lists Cloud Sync across devices under Pro. Its pricing page lists Windows among the desktop platforms and its FAQ names Windows as supported; its setup guide is written for the Mac and names no Windows key. The annual figure is the pricing page's $12 per member per month billed yearly, multiplied by twelve and quoted here as the yearly total; monthly billing is $30.
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 Typeless's own pages say.
| What | Deixis | Typeless |
|---|---|---|
| Audio | Never. Recognition happens inside the app on your device; the recording, the model and the transcript stay there. | Your voice. The privacy policy: audio inputs and contextual information are processed in real time on Typeless's cloud servers and immediately discarded once the transcription result is returned to your device.Typeless's cloud servers · every 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 transcript comes back to your device. History stays on the device unless you enable History cloud sync, in which case history text is stored until you turn it off or delete it. Text handled by third-party LLM providers is configured for zero retention with them, per the policy.your device; Typeless's servers with cloud sync on; third-party LLM providers for the AI features · with each dictation; cloud sync only when you enable it |
| 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 | Limited contextual information: the application you are using and relevant text within it, sent with the audio and discarded once the result is returned. The policy says no screen context data is stored on its servers.Typeless's cloud servers · with each dictation |
| Telemetry and analytics | None. No account, no telemetry, no analytics, no crash reports. | Usage data: IP address, device type, browser type and version, pages visited and system logs; Google Analytics is named as a third-party analytics service.Typeless and Google Analytics · not stated per feature |
| 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 | Nothing to download: recognition runs on Typeless's cloud servers, not on a model on your PC.— · — |
| Account and sign-in | An email address, only if you choose to start the trialthe Deixis endpoint · when you start the trial | An account is required: the setup guide has you sign in with Google, Apple or your email address. The policy lists email address and, for paid plans, payment details handled by Stripe, Apple or Google.Typeless · at sign-up, before the first dictation |
| 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 | not documented |
Before you switch
Before you switch
Who should not switch
If you dictate in a language other than English, stay with Typeless: Deixis's speech models are English models. If Ask anything, built-in translation with no setup, or a tone per app is the reason you use it, those are things Deixis either lacks or asks you to configure. On Windows, Deixis needs a 64-bit Windows 10 or 11 PC from 2013 or later; on an older processor it will not start. And there is no Linux build.
Making the switch
Five minutes, most of it the one download.
The key
Whatever key you gave Typeless, the Deixis gesture is hold Ctrl+Win, speak, release. Double-tap
the chord for hands-free mode, which listens until you double-tap again. The chord can be remapped
in Settings.
The speech model
First launch shows one Download button. Press it, wait for a file about the size of a short video, and you are dictating. Settings offers a second, larger model, more accurate and slower to decode, that swaps in without a restart.
Your words
Typeless's personal dictionary becomes Deixis's: select a word anywhere, press Ctrl+Win+D, done.
There is no importer, so add words as you go, or paste a list into the dictionary file, which is
plain text in your home folder. Five vocabulary packs ship in the box, for software, finance,
business, medicine and law. A word Deixis keeps mishearing gets a replacement rule, fixed once.
Cleanup, translation and the rest
Out of the box, rules on your PC do the tidying. If you liked Typeless's polish on every sentence,
Settings → Cleanup is one choice: Deixis's cloud, a model on your own machine, or your own key, and
what leaves your PC for it is the short list in the table on this page. Translate is Ctrl+Win+T
on a selection and uses the same choice. M records a meeting, S grabs the screen, V records
it.
Your account
Deixis has nothing to cancel, because there was never an account. Your Typeless subscription and anything you synced to its cloud are managed on its side.
Before you ask
Questions people search for
Is Typeless safe?
Its privacy policy says audio and context are processed on its cloud servers in real time and discarded once the result is returned, that no voice recordings are stored on its servers, and that text sent to third-party LLM providers is configured for zero retention with them. That is a reasonable set of promises about what happens after your voice leaves your PC. Deixis makes the shorter one: it never leaves.
Is Typeless free?
There is a free plan of 8,000 words a week at standard accuracy; unlimited words and enhanced accuracy are $30 a month or $12 a month billed yearly. Deixis is free forever for everything that runs on your PC, with no cap and no account; Pro is $49 a year, or $10 a month, for the managed cloud extras.
What does Typeless send from my screen?
Its privacy policy says it sends "limited contextual information, such as the application you're using and relevant text within it" along with your audio, and that no screen context data is stored on its servers. Deixis sends the name of the app and the field, with your own last utterance there, never the text on your screen, and only once you have switched cloud cleanup on.
Does Typeless work offline?
Not for dictation: its policy says recognition happens on its cloud servers. Deixis recognises speech on your own processor, so with no cloud endpoint configured it dictates, records and transcribes meetings, and grabs screens with no connection at all.
Does Typeless need an account?
Its setup guide has you sign in with Google, Apple or your email address as a setup step. Deixis needs no account for anything that runs on your PC, and the cloud extras take an email code only if you choose to start the trial.
What is the best Typeless alternative for Windows?
If the change you want is where your voice goes, Deixis: the same hold-a-key dictation with the recognition on your own processor, no account, no cap, and meetings, grabs and recordings on the same key, on your PC, your Mac and your phone. If you need a hundred languages or Ask anything, Typeless still wins, and this page says so above.
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 Typeless checked on 2026-09-05 against typeless.com. Deixis facts are from its README for the current release. Something out of date? Tell us.