Dictation for Outlook
Email is the longest prose most people write all day. Not the long documents — those are rare — but forty short pieces of writing between nine and six: the reply that has to be tactful, the update nobody asked for, the subject line you rewrite twice before you send it. It is all words, none of it is code, and almost all of it is faster said than typed.
Deixis is voice input for exactly that. Hold Ctrl+Win, say it, let go, and clean punctuated text
lands in the box you were looking at, with your clipboard handed back the way you left it. Say the
subject line and you get a subject line. Say the body one field lower and you get sentences. Deixis
knows which field it is typing into, because the name of the app and the name of the control travel
with your words — never the window title, and never anything on your screen.
That it is not an Outlook feature is the point. Deixis is not a plugin and not an extension for anything: it types wherever your cursor already is, so the one key that dictates your email also dictates your ticket, your chat message, your commit message and your browser's address bar. One voice input for the whole machine, not one per app — on Windows, Mac, iPhone and Android, with speech recognition on the device every time. Your audio never leaves it, under any setting, on any plan.
Why Deixis
What it gives you in Outlook, and what it will not do
Why Deixis in Outlook
- Your voice never leaves the machine. Outlook's own Dictate button is a Microsoft 365 cloud
service, and Microsoft's support page says so plainly: it needs "a microphone and reliable
internet connection", it "is only available to Microsoft 365 subscribers", and "Your speech
utterances are sent to Microsoft and used only to provide you with text results." They say the
service does not store the audio or the text — but sent and then discarded is a different promise
from never sent. Deixis transcribes inside itself, on your own processor, with no account and
nothing to sign in to. Windows' own voice typing on
Win+His the same shape: Microsoft describes it as "online speech recognition, which is powered by Azure Speech services". - A subject line is punctuated as a subject line. Say a subject and you get one line, capitalised, with a question mark if you asked a question and no trailing full stop if you did not. Move one field down and the same voice comes out as sentences and paragraphs, because Deixis knows it is in a body now. A one-word reply stays a one-word reply.
- One key everywhere, including where Outlook's button is not. The Dictate button lives on the Message tab in the desktop app, the new Outlook for Windows, Outlook for Mac and the web — and Microsoft's own page says the feature is being retired from Outlook Mobile from September 2024. Deixis types at the caret, so it works in your inbox, your calendar description, your task list and every other window on the machine, and there is a phone keyboard and an Android bubble that do the same thing.
- Free mode, for the email you have not finished thinking through. Double-tap the key and Deixis keeps listening until you double-tap again. Talk your way through the whole reply, changes of mind and all, and one finished note is pasted at the caret and saved as a file.
- A picture, for the email that needs one.
Ctrl+Win+Sfreezes the screen, you drag a region, and the editor gives you arrows, boxes, a highlighter, numbered step badges and a pixelate tool for the account number that should not be in an attachment. Copy puts a real image on the clipboard, ready to paste into the message. - Show it instead of describing it.
Ctrl+Win+Vrecords the screen with your narration, writes the recording up on your own machine with a title and a short summary, and hands you a link anyone can open without an account of their own. Making the link is the one managed feature, so it needs a Deixis account; every link expires on a date you choose, and you can revoke it. - Meetings, transcribed on this machine.
Ctrl+Win+Mrecords the microphone and, where it can, the other side of the call, and transcribes it here — no account, no network, no key. It tells the remote voices apart and remembers the ones you name, and the voiceprint that does it stays on the machine, is never uploaded, and can be deleted per person. Meeting notes are the one optional step that leaves the machine, and only with an endpoint set. - It learns your customers' and products' names. Select a name anywhere — in a signature, in a
contract, in a reply — press
Ctrl+Win+D, and it is in your vocabulary. Names the model keeps mishearing can be corrected once and stay corrected. Five vocabulary packs ship in the box, including accounting, business, legal and medical ones. - Your own buttons, doing your own work. Add a button to the palette that runs your program with the finished note and types back whatever it prints, straight at the caret — so "log a call with the Deloitte account about the renewal" comes back as the record's reference. Or chain steps together as plain settings: translate, summarise, apply an instruction of your own, post it somewhere. Nothing to script if you would rather not; the panel has ready-made ones a click adds.
- A signed webhook to your own URL. Every finished note, grab or translation can be posted to an endpoint you own, with an HMAC signature and a timestamp so your receiver can prove it came from you and refuse a replay. It retries in the background while your text is already pasted, and your URLs are yours — they do not pass through anybody's cloud.
- Everything is a file you own. Notes, transcripts, recordings, screenshots, your dictionary and every setting sit in one folder as ordinary files, and your dictation history has its own tab with an export. Back it up, search it, uninstall tomorrow and it is all still there.
What it will not do
- It speaks English only. The speech models are English models. Microsoft's page lists fifteen fully supported dictation languages plus a longer preview list, and if you write your email in one of them, theirs is the better tool for that and this is not yours yet.
- It does not know your contacts or your calendar. Deixis is dictation, not an assistant. It cannot complete a colleague's name from your address book, cannot find a free slot, and will not fill in the recipient for you. It types what you said, where you are pointing.
- It does not read your screen. Deixis sends the name of the app and the name of the field, never their contents, so it cannot see the message you are replying to and cannot summarise a thread for you. You still have to say what you mean.
- It will not transcribe a file you hand it. Deixis transcribes what it records — your dictation, your meetings, your screen recordings. Dropping a voice memo or an attachment on it is not in the product.
- No Linux, and no PC older than 2013. The speech engine is compiled against an instruction set that arrived in 2013, so an older processor stops with an error rather than running slowly. Linux is not planned.
- It is not a keyboard replacement. Addresses, symbols and table figures are still faster typed. Deixis is for the prose half of the email, which happens to be nearly all of it.
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.
Field by field
The same voice, punctuated for wherever you are in Outlook
Deixis knows which app and which field your words are going into — the name of the app and the name of the control, never the window title and never what is on your screen. A prompt, a message and a commit line therefore come out differently. Here is the desktop app, the web and the phone, kind by kind.
| Where you are | What you say | What Deixis types |
|---|---|---|
| A subject linethe Subject box of a new message | “um quarterly invoice run is late can we push the friday send” | Quarterly invoice run is late — can we push the Friday send?A subject line is one line. It gets a capital and a question mark, and it does not get split into two sentences or given a trailing full stop. |
| A message bodythe body of the same message, one field below | “hi priya thanks for sending the draft over i've read it and the numbers look right the only thing i'd change is the second table it should show the renewal date not the start date” | Hi Priya, thanks for sending the draft over. I've read it and the numbers look right. The only thing I'd change is the second table: it should show the renewal date, not the start date.The same voice, one field lower, comes out as sentences — because Deixis knows this is a body and not a one-line box. |
| A short replyan inline reply in the reading pane | “yes tuesday works but not before ten” | Yes, Tuesday works — but not before ten.A six-word answer stays a six-word answer. Nothing is padded out into a paragraph you then have to delete. |
| A calendar invitationthe description of a meeting you are sending | “thirty minutes to go through the migration plan um bring the runbook and last month's error counts” | Thirty minutes to go through the migration plan. Bring the runbook and last month's error counts.An agenda is prose, so it gets prose punctuation — and the filler word goes. |
| A task or a note to yourselfa task, a flagged item, or a note in another window entirely | “chase deloit about the renewal quote before the end of the week” | Chase Deloitte about the renewal quote before the end of the week.A customer name the speech model mishears is corrected by your own dictionary, on this machine, before anything is sent anywhere. |
Outlook facts from dictate_outlook, dictate_word, dictate_365, dictate_mobile and voice_typing, read on 7 September 2026. Everything about Deixis on this page is from its README for the current release.
Worth knowing about Outlook
- Outlook has a Dictate button of its own, and Microsoft's own page is plain about what it is: “Dictation in Outlook lets you use speech-to-text to author content with a microphone and reliable internet connection,” and “The dictation feature is only available to Microsoft 365 subscribers.” It is a Microsoft 365 cloud service, not something running on your PC.
- Where the audio goes, in their words: “Your speech utterances are sent to Microsoft and used only to provide you with text results. This service doesn't store your audio data or transcribed text.” Sent, then not stored — which is a different promise from never sent at all.
- Their genuine win is reach. Microsoft's page lists fifteen fully supported dictation languages and a longer list of preview ones, with spoken punctuation and formatting commands in each — say “new line”, “open quotes”, “period”.
- The Dictate button appears on the Message tab in Outlook for Microsoft 365, the new Outlook for Windows, Outlook for Mac, Outlook 2024 and Outlook.com, with a keyboard shortcut of its own — and nowhere else, so it is an Outlook feature rather than a Windows one.
- On the phone it is going away: Microsoft's own page carries the notice that “The dictate feature will be retired from Outlook Mobile starting in September 2024.”
- Windows has its own voice typing on Win+H, and Microsoft says the same thing about it: “Voice typing uses online speech recognition, which is powered by Azure Speech services,” and “To use voice typing, you'll need to be connected to the internet, have a working microphone, and have your cursor in a text box.”
- The same wording appears across the Microsoft 365 apps rather than only in Outlook: the Word page repeats that dictation needs “a microphone and reliable internet connection”, that it “is only available to Microsoft 365 subscribers”, and that “Your speech utterances will be sent to Microsoft and used only to provide you with text results.”
Five minutes
Setting it up
About five minutes, and nothing goes into Outlook at all — no add-in, no permissions dialog, no administrator.
Install and fetch the model
One installer, nothing else to install with it. The first launch shows a single Download button for the speech model — about the size of a short video, fetched once, and checked against its published size and hash before it is kept. After that you are offline unless you choose otherwise.
The gesture
Hold Ctrl+Win, speak, release. That is the product. Double-tap it instead and Deixis keeps
listening until you double-tap again, which is the one for a long reply you are still composing in
your head. If the chord clashes with something in your setup, Settings captures a new one as you
press it.
Hold the chord a moment longer and a small palette appears with a letter per mode: S grabs and
annotates a region of the screen, V records it, M records a meeting, T translates what you have
selected, and D puts the word under your cursor into your dictionary.
Teach it your customers' names
This is the biggest single improvement and it costs nothing in speed. Select a company name, a
product name or a colleague's surname anywhere on screen, press Ctrl+Win+D, and it is in your
vocabulary. A name that keeps coming out wrong gets a correction that lands verbatim, every time,
forever. The Dictionary tab is the same list if you would rather edit it in one place, and the
packs that ship — accounting and finance, business and product, legal, medical, software — are a
click each.
Decide what may leave, once
Settings → Cleanup is the only privacy decision on the page, and its default is the quiet one: rules tidy your words on this machine unless you asked for a transform or dictated a long stretch with no punctuation. Set it to never, or leave the endpoint empty, and dictation never touches the network. Point it at a language model running on your own machine and the better prose stays local too. Whatever you pick, the audio is not part of it — that never leaves, and there is no setting that makes it.
Your own buttons and webhooks, if you want them
Worth ten minutes once. A palette button can run a program with your finished note and paste back whatever it prints, so a dictated summary becomes a logged call and the reference lands at your caret. Your script gets the note as JSON, arguments go to the process as a list so nothing needs escaping, and the first run shows you the exact command line and does nothing until you approve it — edit the command and it asks again. Separately, any finished note, grab or translation can be posted to a URL you own, signed and timestamped, with every attempt shown in the Activity feed.
Before you ask
Questions people search for
Does Outlook have dictation of its own?
Yes — the Dictate button on the Message tab, with a keyboard shortcut of its own. Microsoft's own support page describes it as needing "a microphone and reliable internet connection" and says the feature "is only available to Microsoft 365 subscribers". Their page also says your speech utterances are sent to Microsoft and used only to return text, and that the service does not store the audio or the transcript.
So which one should I use?
If you write your email in one of the fifteen languages Microsoft fully supports, or you like their spoken formatting commands, use theirs. Use Deixis if you would rather the audio never left your machine, if you have no Microsoft 365 subscription, if you want the same key to work in your ticket tracker and your chat as well as your inbox, or if you dictate on the phone — Microsoft's page says the feature is being retired from Outlook Mobile from September 2024.
Will it punctuate a subject line differently from the body?
That is the thing it is best at. Deixis is told the name of the app and the name of the control your caret is in, so a subject box gets one clean line and the body below it gets sentences from the same voice. It never sees the contents of either, and never the window title.
Do I need an account or a subscription?
No. Dictation, both speech models, the dictionary and all the packs, screen grabs, screen recording and meeting transcription are free with no sign-in at all. The optional cloud tidy-up is free too if you bring your own provider key or point it at a model on your own machine. Paying only buys not having to set that up. Sharing a recording as a link is the one thing that needs a Deixis account.
Does it work in the new Outlook, the old one and the web?
All of them, and it does not care which. Deixis types at the caret in whatever window has focus, so the classic desktop app, the new Outlook for Windows, Outlook on the Mac and Outlook in a browser tab all take the same key — as does every other program on the machine.
Will it work offline?
Completely. With no cleanup endpoint set, dictation, free mode, screen grabs and meeting recording and transcription all run with no network at all. Two calls a fresh install makes on its own: the update check, and — when you open the Settings window — a check for an announcement from us. Both send nothing but the request.
Keep reading
Related pages
Teach dictation your vocabulary: names, jargon and acronyms
When dictation mangles names, jargon and acronyms, a custom vocabulary fixes it. How to teach Deixis your words, which to add, and why the list is capped.
Voice input for your product, without the audio leaving your user
Put voice input in your web or desktop app in about ten lines. Recognition runs on your user's machine, so no audio reaches you, us, or any cloud.
Offline dictation on Windows
Dictation that works with no internet: speech recognition on your own device, free, no account. Which Windows speech-to-text tools genuinely run offline.
Dictation for Claude Code
Deixis dictates into Claude Code on one key — terminal, editor, desktop app or browser. Speech recognition on your own device, no account, free.
Dictation for Cursor
Deixis dictates into Cursor on one key — the agent prompt, the editor, the terminal, anywhere else. Recognition on your own device, no account, free.
Dictation for VS Code
Deixis dictates into VS Code on one key — chat, editor, terminal, and every other window on your machine. Speech recognition on your device, 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 Outlook checked on 2026-09-07 against microsoft.com. Deixis facts are from its README for the current release. Something out of date? Tell us.