A library that grows with you
All your skills in one place: cleanups, summaries, formatting, or your own prompt chains. Start from templates and shape them around your voice and tasks.
Offline dictation for Mac & Windows
One hotkey. Dictate into any app. Get an AI answer right at your cursor, on-device by default, cloud only when you choose.
Start with 7 days free · cancel anytime, effective at period end
Parakeet
Ready to dictate
Hold the hotkey and speak
Total Words
48,912
Total Sessions
1,204
Avg. 41 words
Day streak
12
Across all time
Daily Activity
Let's move the review to Thursday at ten and send the agenda around tomorrow morning.
CopyTranscription works offline
And most alternatives make things worse.
Quick project update: the draft is done, the team's feedback is in, and the final version goes out to the client first thing tomorrow morning.Quick project update: the draft is done, the team's feedback is in, and the final version goes out to the client first thing tomorrow morning.
Quick project update: the draft is done, the team's feedback is in, and the final version goes out to the client first thing tomorrow morning.Quick project update: the draft is done, the team's feedback is in, and the final version goes out to the client first thing tomorrow morning.
Typing slows you down. Every app switch breaks your focus. By the time you find the right tool, the idea is gone.
Cloud dictation apps send your voice to remote servers. Built-in OS tools are limited and clunky. Either way, you give up privacy or quality.
A tool that grows with you: on-device by default, cloud speed where you want it, and your own AI building blocks for the tasks you do every day.
Ownvox runs system-wide on Mac and Windows. Wherever a text field is blinking (email, browser, editor, notes or team chat), you can dictate. No copy-paste, no plugins.
Hi Jana, the draft is attached.
I'll be there in ten minutes.
dog-friendly hikes near Lake Tahoe
Minutes: the Q3 budget is approved.
Five tips for more productive meetings
Idea: onboarding in three steps
// Checks whether the session has expired
Review is done, good to ship.
App names and logos are trademarks of their respective owners. See trademark notice.
Typing and asking AI both break your flow. Ownvox closes both gaps, right at your cursor.
You already know the sentence, then spend seconds typing, fixing, and switching apps.
Hotkey, speak, done. Ownvox transcribes on your device and inserts text exactly where you're working, off the cloud by default.
Mode 2 up close: selected text is passed along as context automatically, and the answer lands right at your cursor, no copy-paste.
Browser, editor, notes app. One shortcut and Ownvox is listening.
Say what you need. Highlight text first and it is passed along as context automatically.
The model replies right into your text flow. No window hopping, no interruption.
Skills handle the rest, right at your cursor, no copy-paste.
How it works
Select text, press the hotkey, pick a skill from the radial menu. The AI output replaces your selection right inside the app you are working in. No copy-paste, no tool switching.
The demo runs on its own. Hover a segment or click a skill to try it yourself.
Skill menu
Hover or click a skill
⌘⇧Kopens the menu in any app. The result replaces your selection.
Start from templates, shape them around your voice, and sort them with drag and drop.
All your skills in one place: cleanups, summaries, formatting, or your own prompt chains. Start from templates and shape them around your voice and tasks.
Arrange skills the way you actually work, frequent ones on top, rarely used below. A quick drag is all it takes for the radial menu to surface the skills you reach for in the flow.
Interviews, meetings, lectures, voice memos: drop audio or video files into Ownvox and get the transcript back. Files are always transcribed by a local model on your Mac or PC. Nothing is uploaded, not even when you use the cloud for dictation.
Drag MP3, WAV, M4A, FLAC, OGG, MP4, MOV or MKV files into the Transcripts tab, or pick several at once. Up to 6 hours per file.
Choose any installed model, such as Whisper Large v3 Turbo, and a language, or let it detect one. The queue works through one file at a time and pauses while you dictate.
Copy the transcript, save it as .txt or Markdown, and find it again later in your transcript history.
Local by default, cloud only when you want it. Designed to be GDPR-compliant and made in Germany.
Built for GDPR
Built for EU requirements, transparent processing, DPA on request.
Made in Germany
Developed in Germany.
Privacy switch
One click, all cloud features off. Instantly.
EU infrastructure
Cloud proxy at Hetzner (DE), inference at Scaleway (FR).
In short: by default it stays with you. Cloud only exists if you switch it on for a feature.
Default
Optional
Both plans unlock the same complete product. The only choice is whether you want to start flexibly or lock in the better yearly price.
Billed monthly, cancel anytime.
incl. VAT
€0.00 today. Card or PayPal required, first charge after 7 days. Cancel before then and you pay nothing.
Works out to €5.84 per month, billed once a year, up front.
incl. VAT
€0.00 today. Card or PayPal required, first charge after 7 days. Cancel before then and you pay nothing.
7-day free trial, then the subscription renews automatically at the price shown. Cancel during the trial and you won't be charged; after that, cancel anytime, effective at the end of the billing period. The statutory 14-day right of withdrawal applies. More in the withdrawal policy.
Short answers to the questions people ask before they commit.
One hotkey, one voice, one cursor. Text lands where you're working, instantly.
7 days free, then €9.99/mo or €69.99/yr incl. VAT · cancel anytime, effective at period end