Everything under control
Hotkey, language, microphone, appearance — make the app exactly your own. It understands 9 languages.
Faster than a keyboard
More natural than typing
Save hours of typing every week. Think - speak - combine.
v1.9.0 · Windows 10/11 & macOS
A third of the time
Dictation on the left, keyboard on the right. Each window runs at its own pace — watch the difference add up.
0
Hi, I'm sending over the materials for tomorrow's meeting.
Yes, we're on track — I'll share the draft this afternoon.
Third-quarter results exceeded expectations by twelve percent.
Hello, please find the updated proposal attached.
Client demo and preparing the materials for Thursday.
Call the supplier, order toner and book the meeting room.
best restaurants nearby open on Sunday
Great video, especially the part about the mic setup.
Sure, but last one — I'm done at ten.
0:03
By voice
0
Hi, I'm sending over the materials for tomorrow's meeting.
Yes, we're on track — I'll share the draft this afternoon.
Third-quarter results exceeded expectations by twelve percent.
Hello, please find the updated proposal attached.
Client demo and preparing the materials for Thursday.
Call the supplier, order toner and book the meeting room.
best restaurants nearby open on Sunday
Great video, especially the part about the mic setup.
Sure, but last one — I'm done at ten.
By keyboard
How it works
No window switching, no copy-pasting. Three steps — and you're typing with your voice.
01
Hold the shortcut
Set your own global shortcut — just hold it.
02
Speak
The equalizer shows you it's listening. Just speak naturally.
03
Release
Let go and your text lands instantly, right where your cursor was.
Built for speed and productivity.
A powerful tool you don't see until you need it.
Ready
Recording indicator
While you speak, an indicator with an equalizer pops up — and disappears once your text is inserted.
0.3–1.1 s
from speech to finished text — depending on length
Built for speed
The system is always ready in the background.
One dictation, many shapes
Modes rewrite your voice into whatever you need right now — from a raw transcript to a ready-to-send email.
8 built-in modes + custom modes with a personal dictionary.
Text processing
Raw Clean Email Chat To-Do Translate
You said
„remind the team about tomorrows demo at ten and i still need to send the report"
Remind the team about tomorrow's demo at 10:00. I still need to send the report.
Quiet in the background
Lives in the tray icon and can start with your system. Uses just ~90 MB of RAM.
History & statistics
Look up any past transcript, and the app counts the time you've saved. All stored locally.
Private by design
The microphone opens only while you hold the hotkey. Your API key and history stay with you.
Works in every app
Browser Email Code editor Chat Documents Gaming
Your key - your control
Dictation runs on your own Groq API key — free and no strings attached. No credit card or phone number needed.
Set up in a minute
- 01 Create a Groq API key — free, in a few seconds. Official link: console.groq.com/keys
- 02 Paste it into the Online tab and hit Test.
- 03 Done... Now just dictate.
The key is stored only on your computer
The mic runs only while you hold the hotkey
Watch your usage live in Statistics
Hit a limit? Dictation keeps working
Groq limits
More than enough headroom
Three Groq models run under the hood — when one hits its daily limit, the app switches to the next automatically:
whisper-large-v3 Transcription
8 h of audio per day · 2,000 dictations
llama-3.3-70b-versatile Post-processing
100,000 tokens per day
On by default — cleans up grammar, punctuation and structure.
openai/gpt-oss-120b Backup
200,000 tokens per day
Kicks in automatically once the first model runs out for the day.
Go over and there are no charges or commitments — the limit simply resets.
Prefer no key at all? A fully offline local mode is in development.
What's new and what's next...
The current version, fresh features and what's in the works right now.
CHANGELOG.md main
next coming soon
- Planned Fully offline local mode — dictation with no key and no internet
- Planned Linux app
v1.9 current
- New macOS app (Apple Silicon & Intel)
- New 8 text modes + custom modes — Clean, Email, To-Do, Translate, Assistant…
- New Personal dictionary — your names and terms, always spelled right
- New History & statistics — transcripts and time saved, stored locally
- New 9 recognition languages, interface in 5
- Improved Automatic model fallback — up to 3× the daily capacity
- Improved Mic runs only while the hotkey is held; hotkey survives sleep & fullscreen
- Fixed Silent recordings paste nothing — no more invented text
v1.0+ earlier
- New Windows desktop app
- New Push-to-talk dictation in every app
- New Your own Groq API key — stored locally
- New Optional AI post-processing
Frequently Asked Questions
Which applications does it work with?
It works in every Windows application — browser, email, Slack, VS Code, Word, notes. Wherever you place the cursor, the text will appear there.
Which languages does it support?
Slovak, Ukrainian, and English — all processed with the same accuracy and natural quality. No compromises, no favorites.
Why do I need to create my own API key?
Because it is a very effective alternative to traditional STT solutions and LLM-based postprocessing. We also take into account that not every user has a powerful enough device to run large LLM models locally. Nevertheless, we are actively working on local processing and optimization for different types of devices. The current solution provides significantly higher quality and faster processing without unnecessarily using your device's resources. Modern LLM models for text processing are very powerful, and thanks to the optimized infrastructure on Groq servers, they can deliver fast and high-quality results.
Where is my API key stored?
Exclusively on your device. It never passes through our servers — we cannot see it and we never send it anywhere. Control remains entirely with you.
Do I need to switch between windows?
Not at all. The text is inserted exactly where your cursor was. If something goes wrong or you forget to select a field, the text remains in your clipboard — just press Ctrl+V.
Will it slow down my computer?
No. The application uses around 90 MB of RAM, which has no noticeable impact on performance or FPS. It runs quietly in the background and does not interfere with your work.
Is my voice recording private?
Yes. The recording goes directly from your device to the Groq API — we never see or store it. Your voice, your data.
Do I need an internet connection?
Yes. An internet connection is required for voice processing, but the application itself runs locally.
What is postprocessing?
After transcription, AI automatically corrects grammar, punctuation, and text structure, so the result sounds natural and clean without additional editing.
How do I get an API key?
Register for free on Groq, create an API key, and add it to the application. The entire process takes approximately 2 minutes.