Dimmy: voice dictation, command mode, and AI meeting recaps for macOS and Windows

latest · now on mac & windows
Detto, fatto. said, done.

A voice power tool for macOS and Windows. Dictate clean text anywhere, speak commands that edit in place, and turn meetings into structured recaps. Offline by default.

what dimmy actually does

You think it. You say it. Dimmy makes it useful.

One voice in, three kinds of finished work out: clean text where your cursor is, edits made in place, and meetings turned into recaps you can share.

your thoughts
+ your voice
01 · Dictation↓
"uhm so tell the team that like the new build is ready for testing tomorrow morning"
transcribe locallypolishpaste at cursor
Slack · #designCLEAN TEXT
Heads up, team: the new build is ready for testing tomorrow morning.
02 · Command Mode
select text, then say:
"make it more formal and shorter"
read selectionapply instructionreplace in place
Docs · ProposalEDITED IN PLACE
we need the numbers asap or this whole thing slips
Please share the figures by Friday to keep the timeline.
03 · Meetings
47-minute call, both sides of the conversation, no bot joining
recordtranscribe liverecapsend anywhere
Recap · Q3 planningSTRUCTURED RECAP
DECISIONS
  • Launch moves to Oct 14
  • Beta stays invite-only
ACTION ITEMS
  • Anna: pricing page draft, Fri
  • Luca: fix onboarding bug
→ Notion→ Obsidian / Drive folder→ Claude via MCP
see it work

Your voice goes in. Finished work comes out.

you say
uhm so tell the team that like the new build is ready for testing tomorrow morning
Speak
Transcribe
Polish
Paste
Slack · #design
Marta 10:42
any news on the build?
now try it yourself
HoldSpaceor tap the pill below. Try it right here.
~/work/draft.txtready
Hold Space and say something.e.g. "draft a reply saying we're aligned and want to ship by Friday."
local models or your cloud key·whisper · parakeet·offline when you choose local
Let your AI assistant install it

It downloads Dimmy, asks what you need it for, sets it up and tests it with your voice. You only click the system permissions.

AppOpen your assistant with the request ready

The button opens Claude Desktop or the Codex app with the request written in. Read it and press Enter.

TerminalOr run one of these
$claude "Install Dimmy on this computer by following https://dimmy.app/install.md"
$codex "Install Dimmy on this computer by following https://dimmy.app/install.md"

Needs Claude Code or the Codex CLI. The assistant follows this guide.

Or install it yourself on Windows
Direct downloadsigned .exe · dl.dimmy.appDownload →
winget
$winget install Dimmy.Dimmy
Installs the latest release.
Microsoft StoreOpen →
free from source·open source·telemetry off unless you say yes·no account·~135 mb installer
3
voice superpowers
4
writing tones
13
rewrite styles
100+
apps it works in
scroll to explore
works everywhere

If it has a text input, Dimmy works in it.

Slack
Notion
VS Code
Figma
Discord
Linear
Gmail
Cursor
Terminal
Obsidian
ChatGPT
Claude
Microsoft Word
Google Docs
Telegram
Whatsapp
Things
Bear
Xcode
Safari
Chrome
Arc
Mail
iMessage
Zed
Sublime
JetBrains
Slack
Notion
VS Code
Figma
Discord
Linear
Gmail
Cursor
Terminal
Obsidian
ChatGPT
Claude
Microsoft Word
Google Docs
Telegram
Whatsapp
Things
Bear
Xcode
Safari
Chrome
Arc
Mail
iMessage
Zed
Sublime
JetBrains
01live demo

Press, speak, release.
That's the whole UX.

One icon, one status dot, a right-click menu. That's all the UI you ever need to see. Watch it cycle live.

DimmyFileEditViewWindowHelpFri 1 May 20:21
ready
Tasks
Toggle pill
Open Settings…
Quit Dimmy
Style
Off
Correct
Summarize
Elaborate
Comprehensible
Professional
Prompt
Gen Z
Boomer
Emoji
Acronyms
Imbruttito
Custom
Translate to
No translation
🇬🇧English
🇮🇹Italiano
🇫🇷Français
🇩🇪Deutsch
Dimmy (Dev)
Hide menubar icon
real ui · pure react · no video·auto-cycling: idle → rec → transcribe → done·click the icon to toggle the menu
PILLAR 01Dictationspeak → clean text
two passes · local or cloud

Transcribe.
Then enhance.

Two models work back-to-back. One catches every word, the other makes it read like you wrote it. Choose local models for both and it runs on your laptop: no API key, no login, no audio leaving your machine. The local cleanup model is optional, about 2.5 GB.

PASS 1
Transcribe
Catch every word, in up to 99 languages with Whisper.
Offline if localYour choice of modelWhisper: 99 languages
raw transcript
"hey can you draft a quick reply saying we are aligned and we want to ship by friday"
powered by Whisper, Parakeet, or your cloud provider
PASS 2
Enhance
Polish the punctuation, fix the grammar, switch the tone.
13 stylesNo API keyYours to keep
enhanced output
"Hey, can you draft a quick reply saying we're aligned and want to ship by Friday."
powered by A local LLM offline, or a cloud LLM
with local models:on your machineno API keyworks on a plane
0213 styles

One sentence. Thirteen tones.

Pick a style before you press the hotkey. Dimmy will rewrite your speech in the tone you chose, including imbruttito, our love letter to Milanese grumpy.

you said
"ok so thursday afternoon design review with the team sound good"
Professionalpolished, business-appropriate tone

I'd like to propose a design review on Thursday af

auto-cycling. Click any style to lock.
03one click away

Right-click the tray.
Switch styles.

Drafting an email? Email. Notes for yourself? Off. Voice memo to flatten into bullets? Bullets. The tray shows your favorites. 13 styles total, all configurable.

🇬🇧🇮🇹🇫🇷🇩🇪🇪🇸🇮🇹+ napoletano
Translate while you dictate.
Speak Italian. Output English. Or napoletano, perché no.
Tasks
Toggle pill
Open Settings…
Quit Dimmy
Style
Off
Correct
Summarize
Elaborate
Comprehensible
Professional
Prompt
Gen Z
Boomer
Emoji
Acronyms
Imbruttito
Custom
Translate to
No translation
🇬🇧English
🇮🇹Italiano
🇫🇷Français
🇩🇪Deutsch
Dimmy (Dev)
Unpin from taskbar
Close window
← five styles
  one click
04no pill, no problem

Hide the pill.
The tray icon takes over.

You're presenting on a Zoom call. You're recording a Loom. Or you just don't want a colored pill floating at the edge of your screen all day. Toggle it off. The tray icon does everything the pill did, quietly.

Windows · taskbar
macOS · menu bar
Fri 1 May 14:32
auto-cycling · ready · nothing on screen
Screenshare-safe
Nothing floats over your slides. Recording is invisible to viewers, but the tray tells you it's on.
Fullscreen-friendly
Games, video editors, presentations. Apps that hate floating overlays still get dictation.
Distraction-free
Some users just don't want a pill in their peripheral vision. The tray icon is enough.
05it's a real app

Settings that
respect your attention.

No 7-step onboarding. No account. Search, click, change. Done. Click around. It's the real thing.

live prototype · click anywhere · theme follows the page
Live preview
See pill states before applying
9-grid position
Snap anywhere, drag to fine-tune
Border styles
Rainbow, solid, breathing, off
Per-app rules
Different shortcut, different style
06two minutes to setup

Pick your engine.
Cloud-fast or fully offline.

Groq's free tier is genuinely the fastest cloud STT we've benchmarked. A local model is fully private and works on a plane. Both are first-class.

1
Sign up at console.groq.com
No credit card. Free tier covers ~100k tokens/day, way more than you'll use.
🔒 console.groq.com
Welcome to Groq
The fastest LLM inference on the planet.
Sign in with Google
2
Create an API key
🔒 console.groq.com/keys
API Keys
namedimmy+ Create key
gsk_•••••••••••••••••••••••••••••••• 7Hk2
3
Paste it into Dimmy
Settings → Transcription → Cloud (optional) → Groq API key. Stored in an encrypted file on your computer. Done.
⚡
That's it. Transcription now runs at Groq, with your key, so your machine does almost no work.
07privacy

Your voice can stay
on your machine.

Dimmy can run fully offline when you choose local models. A cloud provider is used only when you pick it, with your own key. We don't need to know who you are.

Off
telemetry, until you say yes
usage counts and crash reports under a random, pseudonymous ID. never your audio or your text. two separate switches.
0
sign-ups to dictate
no user account. a licence uses only the e-mail you buy with.
Local
where recordings are kept
dictation audio is not kept unless you turn on audio in history. meeting recordings are saved on your computer.
Encrypted
api keys, in a local file
AES-256-CTR + HMAC-SHA256, key derived from your computer. sent only to the provider you picked.
# what dimmy connects to, and when
→ the cloud stt / llm providers you pick, with your key
→ huggingface.co + github.com: model and engine downloads you start
→ github.com: update checks
→ license.dimmy.app: trial and licence activation, refresh
→ posthog eu + sentry eu: only if you turned telemetry on
→ notion, confluence, telegram: only if you connect them
Read the full privacy policy# see what we collect
08pricing

Honest pricing.
No dark patterns.

The code is public. If you can compile, you don't owe us anything. Paying gets you the signed binary, one-click updates, early access, and a human on email. Same software, different distribution.

Free
€0forever

Clone the repo, compile it yourself. Full app, no paywall.

Get the source
✓Same code as Pro. Zero feature gates.
✓You compile, sign, and notarize yourself
✓Local Whisper transcription, all 13 styles
✓Bring your own API key (Groq, OpenAI, Deepgram, Gemini)
✓macOS, Windows
✓Community support on GitHub Issues
most popular
Pro
€39/ yearsave 35%

We compile it for you. You get updates, early access, and a human on email.

I'd buy this
✓Pre-built binary, signed and notarized
✓Auto-update inside the app, one click
✓Early access to beta builds before public release
✓Email support · a human replies in <24h
✓Vote on the public roadmap
✓Cancel anytime, 30-day refund
pay once · 3 years
Supporter
€99once · 3 years

Pay once. Everything in Pro for 3 years from purchase. No subscription, no renewal, no upsell.

I want to support Dimmy
✓Everything in Pro for 3 years · no renewals
✓After 3 years the version you have keeps working
✓Prebuilt for macOS · Windows
✓Priority email support · founder replies
✓Your name in the credits if you want
Three years of updates, paid once. No renewals to forget, no subscription anxiety.
not on sale yet · tell us which plan you'd pick
09manifesto

We built Dimmy
because we were tired.

Tired of voice apps that take ages to wake up and want a subscription to do something a hotkey should do. Tired of giving our voice to a server we'll never see.

So we wrote it native. SwiftUI on macOS, WinUI 3 on Windows, a shared Rust core for the parts that matter. The source is public on GitHub, under the AGPL-3.0.

With local models, audio never leaves your machine. It goes out only when you pick a cloud provider, with your own key. That key is kept in an encrypted file on your computer, and you can remove it whenever. Dictation audio is not kept unless you turn on audio in history; meeting recordings are saved on your computer.

Made with espresso. /ˈdɪmmi/: "tell me", in Italian.

A team of nerds in Italy
native desktop apps, pair-built with Claude Code
♥ Sponsor on GitHub
10roadmap

Mobile when you
want it badly enough.

We can't ship five platforms in parallel. Vote and we'll prioritize. The first platform to hit 1,000 ★ on GitHub gets built next.

iO
iOS
system-wide dictation replacement
An
Android
gboard alternative + system input
Ap
Apple Watch
tap, speak, send to phone
vi
visionOS
the obvious one
votes are stored in your browser, not on our server (because we don't have one)
11frequently asked

Yes, but really, how?

Yes, if you compile it yourself. The whole code is public on GitHub and builds on macOS and Windows. Pro and Supporter sell you the convenience: a signed pre-built binary, one-click in-app updates, early access before public releases, and a human on email. Same software, different distribution.
You pick a local speech model and Dimmy downloads it once. Whisper runs on ggml, from Base (78 MB) to Large v3 Turbo (about 574 MB); on a Mac the default is Parakeet on the Neural Engine. After the download, dictation needs no internet. Speed depends on your machine and the model you choose.
Dimmy can run fully offline when you choose local models. If you connect a cloud provider (Groq, OpenAI, Deepgram, Gemini, …), your audio or text goes to that provider with your own key. The key is stored in a local file encrypted with AES-256-CTR and HMAC-SHA256, under a key derived from your computer. Dictation audio is not kept unless you turn on audio in history. Meeting recordings are saved on your computer. Telemetry is off until you say yes.
Because we wrote it native, one platform at a time, with a shared Rust core for the parts that matter. The Windows installer is about 135 MB and the macOS disk image about 55 MB; speech models are downloaded separately, only the ones you pick. The harder path was the right path.
Mobile is the most-requested feature by a mile. We'll ship the platform that crosses 1,000 ★ on GitHub first. Vote up above.
It depends on the speech engine. Whisper supports 99 languages and detects the language on its own; Parakeet covers about 25 European languages; cloud providers have their own lists. Mixing languages in one sentence works best with Whisper and the cloud engines.
Yes. The 'Prompt' style structures speech as an LLM prompt; the 'Comprehensible' and 'Professional' styles work great for commit messages and doc strings. People mostly use it for Slack, email, and ChatGPT though.
Instead of typing what you say, your speech becomes an instruction Dimmy runs in place. Select some text, say "make it more formal" or "translate to English", and it rewrites the selection right where it sits. With nothing selected, your words become a writing request inserted at the cursor. Same model as the AI styles (local, a cloud key, or your Claude / ChatGPT subscription), on Windows and macOS.
Yes. The Dimmy Meeting window records both sides of a call (microphone + system audio), transcribes live, and the moment you stop writes a structured recap: TL;DR, key decisions, action items, open questions, with timestamps. The audio file and the transcript are saved on your machine and are full-text searchable; with a cloud speech provider, the audio is also sent to it for transcription. Export a recap to Notion, a synced folder (Obsidian, Drive, Dropbox), or Claude Desktop, and the dimmy-mcp bridge lets Claude list, read, search, and save recaps.
Short for 'dimmi', Italian for 'tell me'. We're Italian. We thought it was cute. We're aware that's a bias.

Dimmy.

Italian for "tell me."

Download for Windowswindows 10 · 11 · x64