Alternatives

Win+H, but on your own PC

Windows already has voice typing built in: press Win+H, talk, and text appears. It costs nothing and it is a fair place to start. It also, in Microsoft's own words, uses online speech recognition powered by Azure Speech services, and needs an internet connection to work at all. Every sentence you dictate is sent to Microsoft to be turned into text. If that is fine for you and you never need more than punctuation, keep it. If you want the same gesture with the recognition on your own processor, plus a dictionary, cleanup and a few things Win+H does not do, this page is for you.

Deixis is one small installer for 64-bit Windows 10 or 11, and one download of the speech model on first run. After that, hold Ctrl+Win, speak, release, and clean text is typed at your cursor in whatever app has focus, with the clipboard put back afterwards. No account, no connection needed, and everything that runs on your PC is free for good.

This page is honest in both directions. Windows voice typing wins on languages, on being already there, and on Microsoft maintaining it. Everywhere else, the case for Deixis is short and it starts with where your voice goes.

Why switch

What you gain, and what you give up

Why Deixis

  • Your voice stays on your PC. Microsoft's privacy page says online speech recognition sends voice data to Microsoft to provide the service and create the transcription, and its voice typing page says the feature needs an internet connection. Deixis recognises speech inside the app, on your processor; the recording, the model and the transcript never leave the machine. So it works offline: dictation, hands-free notes, meeting recording and transcription, screen grabs and screen recording all run with the network off, where voice typing stops working the moment the connection does.
  • One tool, on every device you own. Win+H lives on Windows and nowhere else. Deixis runs on 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.
  • It learns your words. Microsoft's voice typing page lists settings for automatic punctuation, a profanity filter, the microphone and the launcher, and nothing for adding a word of your own. Deixis has a dictionary you add to without leaving what you are doing, select a word and press Ctrl+Win+D, plus five vocabulary packs for software, finance, business, medicine and law, plus replacement rules for anything it keeps mishearing.
  • It cleans up what you said. Voice typing gives you the words and, if you switch it on, automatic punctuation. Deixis strips filler words, punctuates and cases the text with rules on your PC, and can hand a sentence to a language model when the rules are not enough, in Deixis's cloud, on your own machine, or with your own key, as often as you choose.
  • It knows what you are typing into. A commit message, a chat reply and a ticket read differently. Deixis knows which app and which field the text is going into and punctuates accordingly, and the only context that ever leaves is the name of the app and the field, with your last utterance in that field so a name stays spelled the way you dictated it; never the window title, never a screenshot, and only if you turned cloud cleanup on.
  • A hold, not a toggle. Win+H opens a listening bar you switch on and off. Deixis is hold to talk: hold Ctrl+Win, say the sentence, let go, and it is typed. Double-tap for hands-free when you have a paragraph in you.
  • Meetings that know who is talking, grabs and recording, on the same key. Ctrl+Win+M records 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, from a voiceprint that stays on your machine, is never uploaded, and can be deleted per person. S freezes the screen for a grab you can annotate with arrows, boxes, numbered steps or a blur. V records the screen to a video, narrated when a microphone is set up for it. Voice typing types; that is all it does.
  • Everything is a file you own. Every note, transcript, grab and recording sits in one folder as ordinary files, and the history is yours to search and export. Microsoft's page describes no history for voice typing: what you said is typed, and that is the end of it.

Where Windows Voice Typing still wins

  • It is already installed. Nothing to download, nothing to trust. Press Win+H on any Windows 10 or 11 PC with a microphone and an internet connection and it works. Deixis is one installer and one model download, which is still two more steps than none.
  • Forty-odd languages. Microsoft's support page lists voice typing languages from Bulgarian to Vietnamese, with several regional variants of English, Spanish, French, Portuguese and Chinese. Deixis ships English speech models only.
  • Microsoft maintains it. It ships with Windows and is patched with Windows, and its page asks for nothing beyond Windows 10 or 11, a microphone and a connection. Deixis needs a 64-bit PC from 2013 or later.
  • Voice commands for editing. Microsoft's page documents commands such as "delete that" and "select that", and pressing keys by voice. Deixis is built around dictating and pointing rather than driving the cursor by voice.

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

Windows Voice Typing and Deixis, side by side

Row Deixis Windows Voice Typing
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 11, Windows 10
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. None
Leaves your machine Text only, and only once you switch a cloud feature on. Never audio, never screenshots, never window titles. Audio
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: included with Windows
Your transcripts live In plain files, in one folder you own and can back up. Uninstall Deixis and every note is still readable. not documented
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. Settings for automatic punctuation, a profanity filter, the default microphone and the launcher. Microsoft's page lists no way to add your own words, no custom commands and no integrations.

Windows Voice Typing facts from its docs, its privacy policy, clips, dashboard, voiceaccess and troubleshooting, read on 5 September 2026. “Not documented” means those pages did not say.

Voice typing is the Win+H feature and is online only: Microsoft's support page says it uses online speech recognition powered by Azure Speech services and needs an internet connection. Microsoft's separate Voice access feature works without an internet connection once its language is downloaded, but its FAQ lists only English, Spanish, French and German for it, and it is a control feature rather than the dictation one compared here. Contributing voice clips for Microsoft to sample is opt-in and off unless you turn it on, per Microsoft's speech privacy pages.

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 Windows Voice Typing's own pages say.

What Deixis Windows Voice Typing
Audio Never. Recognition happens inside the app on your device; the recording, the model and the transcript stay there. Your voice. Voice typing uses online speech recognition, and Microsoft's privacy page says voice data is sent to Microsoft to provide the service and create the text transcription. Microsoft says it does not store, sample or listen to voice recordings without your permission.Microsoft's Azure Speech services · every time you dictate; an internet connection is required
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 not documented
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 not documented
Telemetry and analytics None. No account, no telemetry, no analytics, no crash reports. Nothing unless you opt in to contributing voice clips. If you do, clips are stored de-identified, not associated with your Microsoft account or any other Microsoft ID, kept for up to two years, and may be reviewed by Microsoft employees and vendors to improve speech recognition.Microsoft · only if you turn on contributing voice clips
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: voice typing recognises speech online rather than with a model on your PC, which is why it needs an internet connection.— · —
Account and sign-in An email address, only if you choose to start the trialthe Deixis endpoint · when you start the trial not documented
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

The same table for every tool we have measured

Before you switch

Before you switch

Who should not switch

If you dictate in a language other than English, keep voice typing: Microsoft's list is long and Deixis's speech models are English. If your PC is from before 2013, or a processor without the instruction set Deixis is compiled for, it will not start; voice typing asks for nothing beyond Windows 10 or 11. There is no Linux build either. If you only ever need a sentence or two, punctuated, and you are comfortable with it going to Microsoft's servers, the built-in feature is the right choice: it costs nothing, it is already there, and it asks nothing of you. And if you rely on voice commands to edit and move the cursor, that is not what Deixis is for.

Making the switch

Nothing to migrate: Microsoft's page describes no dictionary and no history to carry over. Here is what changes.

The key

Win+H becomes Ctrl+Win, held rather than toggled: hold, speak, release. Double-tap it for hands-free mode, which listens until you double-tap again and then pastes the finished note. You can rebind the chord in Settings if something else on your machine uses it. Voice typing keeps working alongside; nothing is replaced or disabled.

The speech model

The installer is small. On first launch Deixis shows one Download button for the speech model, a file about the size of a short video, fetched once. Until it finishes there is no model and Deixis says so. Settings offers a second, larger model that is more accurate and slower to decode, swapped in without a restart.

Punctuation and cleanup

Voice typing's automatic punctuation becomes Deixis's rules, on by default and running on your PC: filler words dropped, sentences punctuated and cased. If you want a language model to polish the prose, 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.

Your words

The first thing worth doing. Select any word Deixis got wrong, press Ctrl+Win+D, and it is in your dictionary. Switch on the vocabulary pack for your field. The dictionary is a plain file in your home folder, so a list of names can go in all at once.

The rest

Ctrl+Win+M for a meeting, S for a screen grab, V for a screen recording, T to translate a selection once you have given it a cloud endpoint, your own key or a model on your own machine. All of it lands in one folder as files you can open with anything.

Before you ask

Questions people search for

Is Windows voice typing private?

Microsoft's privacy page says that online speech recognition, which voice typing uses, sends your voice data to Microsoft to provide the service and create the text, and that Microsoft does not store, sample or listen to recordings without your permission; contributing voice clips for people to review is a separate opt-in. So your voice is sent, and by default it is not kept. Deixis never sends it in the first place: recognition happens on your PC, under every setting.

Can I add custom words to Windows voice typing?

Microsoft's voice typing page documents settings for automatic punctuation, a profanity filter, the microphone and the launcher, and no way to add your own vocabulary. Deixis has a dictionary you add to with one key press, five vocabulary packs, and replacement rules for words it keeps mishearing.

Is Deixis free like Windows voice typing?

Yes, for everything that runs on your PC: dictation, hands-free notes, the dictionary and all the vocabulary packs, screen grabs, screen recording and meetings, with no account and no cap. Pro, at $49 a year or $10 a month, adds the managed cloud extras; with your own provider key, those cost nothing from Deixis either.

Does Windows voice typing work offline?

No. Microsoft's support page says you need to be connected to the internet, because voice typing uses online speech recognition. Deixis recognises speech on your own processor, so it dictates, records and transcribes with no connection at all.

Why is Windows voice typing not working?

Microsoft's troubleshooting page points at the microphone: which one is selected, whether voice typing has permission to use it, its input level and the noise around you, and whether your language is on the supported list. Its voice typing page names the other requirement, an internet connection, because the recognition happens online. If that is the one you keep hitting, Deixis is the fix, because it needs none.

What does Deixis send that voice typing does not?

Less: voice typing sends your voice to Microsoft every time you dictate, and Deixis sends nothing on its own except an update check that carries only the request. Only if you switch on a cloud feature does text leave, and the full list, every byte, is in the table on this page.

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 Windows Voice Typing checked on 2026-09-05 against support.microsoft.com. Deixis facts are from its README for the current release. Something out of date? Tell us.