For Mac · Windows · iPhone · Android

Your voice.
Your words, typed.

Hold a key. Speak. Release. Dictio turns what you said into clean, punctuated text and types it right where your cursor is, in any app, on any of your devices.

MailSlackCursor
⌘ holdhold to talk
Listening…
You speak naturally. Dictio types it cleanly. In any app.

Three steps, no learning curve

1

Hold.

Press and hold the hotkey. A small waveform appears so you know it's listening.

2

Speak.

Say what you mean. Emails, prompts, tickets, messages, notes. Any of 50+ languages.

3

Release.

Your words land in whatever text field you were in, cleaned up and ready to send.

Wherever you type

Dictio isn't a separate window you dictate into and copy from. It types into the app you're already using, on Mac, Windows, iPhone, and Android. If the cursor blinks there, Dictio can write there. And everything is copied to your clipboard too, so nothing is ever lost.

VS CodeTerminalSlackChromeMailNotesNotionWhatsApp WebClaudeChatGPTCursorAnywhere the cursor blinks
Speed

Talking beats typing. It's not close.

The same sentence, typed versus dictated. Timed, not estimated.

Typing~40 WPM
Dictio~150 WPM
Built for how you actually work

Dictate your next prompt, not just your next email.

Use Dictio with Claude Code, Cursor, Copilot, or any tool with a text field. No plugin, no integration, no touching your keyboard.

Works wherever you type

Terminal, IDE, browser, chat. If it takes text, Dictio pastes into it. No special integration required.

Long prompts, spoken not typed

Describe the architecture, the edge case, the constraint. Out loud, at around 150 words per minute, while the cleanup strips the filler words for you.

Claude Code
~/Dev/api-backend · Dictio active
> In metering.py can you add a daily spend cap check before the transcribe call. Read the limit from env and return a clear error if we're over it, not a silent failure like it is now.
Hold to dictate · release to paste
Privacy

Your voice stays yours

Dictio works with your own OpenAI API key. Your audio goes straight from your device to OpenAI under your key, and it never passes through our servers. We can't hear you, we can't store you, and we have nothing to train on.

Key in the system keychain

Stored where your passwords live. Never written to a plain file.

History lives on your device

Recordings and transcripts stay local, for your eyes only. Delete them whenever you like.

Read exactly how your audio travels →

Where your audio goes
💻Your devicerecords locally
🔑OpenAIunder your own key
✍️Your text fieldtyped where you were
Zehntech servers: never in the path
No account, no telemetry, no training on your voice
50+languages
Every appyou type in
Your keyyour audio, your control
Nativeapps, light and fast

Straight answers

The questions everyone asks before their first dictation.

Which platforms does it run on?

Mac, Windows, iPhone, and Android. One purchase covers your devices.

Is there a subscription?

No. $19 is the whole price for the app. Transcription runs on your own OpenAI key, and you pay OpenAI only for what you actually use, which for most people is a few cents a day.

Where does my audio go?

Straight from your device to OpenAI, under your own API key. It never passes through Zehntech servers, and we have no way to hear, store, or train on anything you say. Full details on the privacy page.

Do I need an account?

No account, no sign-up. Install the app, add your OpenAI key, and start dictating. Creating a key takes about two minutes, and we show you how right after install.