Skip to content
SpeechToWork
100% local · GDPR-compliant without the cloud

Windows dictation software that writes properly and shares nothing

SpeechToWork is Windows dictation software for work. You hold a key and speak. It writes into the program where your cursor is and tidies up the wording as it goes. Speech recognition and AI run on your PC, on Windows 10 and Windows 11.

Woman dictating into her Windows PC at her desk
  • ≈ 1 sfrom releasing the key to the finished text, measured on our test computer.
  • 25languages the software detects automatically.
  • 100%stays on your computer. Nothing is sent to the internet.
An example

What you say. What appears.

You sayPlease transfer the amount by the fifteenth, no sorry, by the twentieth of October to the account shown on the invoice.
In your programPlease transfer the amount by 20 October to the account shown on the invoice.

Why Windows voice typing is not enough for office work

Windows comes with its own voice typing under Win+H. For a quick note, that is fine. In daily work, three things get in the way: the text comes out word for word, with every “um” and every repetition. You have to say the punctuation. And online speech recognition sends your voice to Microsoft.

SpeechToWork is dictation software built for work. Recognition runs locally, and a language model on your computer puts the text into shape before it is inserted.

How to dictate text into any program

There is no plugin and no integration. SpeechToWork remembers the window that was active when you pressed the key and inserts the finished text there. That works in Outlook, Word, Excel, Teams, Slack, your browser, Sage and your industry software. It also makes SpeechToWork practical dictation software for Word.

  • Spoken punctuation and “new paragraph” are carried out.
  • Numbers appear as digits: 1,500 units, £12.50, 3%.
  • Filler words and slips disappear, your tone stays.
  • If you want it word for word, switch the rewriting off with one click.

Which computer does the software need?

Speech recognition runs on any current office PC and needs no graphics card: in our tests, a twelve second dictation was recognised in half a second. On start, SpeechToWork checks what the computer can do and picks the right language model. With a dedicated graphics card with 6 GB or more, the finished text appears in your program about one second after you release the key; on laptops without a graphics card, after a few seconds.

Your advantage

Why SpeechToWork fits this job.

Writes, not just transcribes

“By Wednesday, no, by Thursday” becomes “by Thursday”. That saves the clean-up that has made dictation unappealing until now.

Knows your terms

Add clients, products and technical terms to the dictionary. From then on they are always spelt correctly.

Edits what is already there

Select text, hold the edit key: shorter, more formal, in German. Or dictate a reply to the selected email.

Privacy

Local means local. No compromises.

Speech recognition and the language model are installed on your PC and run there. What you dictate ends up in your program and nowhere else. How the data flow works.

No upload

Audio and text stay on your computer. There is no server listening in and no AI provider in the background.

GDPR made simple

No third party processes your dictations. So there is no data processing agreement to sign and no international transfer to assess.

Works without internet

Once installed, SpeechToWork works offline. Only the licence check needs a connection.

Good to know

Frequently asked questions

Does the dictation software work on Windows 11 and Windows 10?

Yes. SpeechToWork runs on 64-bit Windows 10 and Windows 11. The installer is about 66 MB. On first start, 4 to 6 GB of language models are added depending on your computer, plus just under 1 GB if you read receipts. You need no administrator rights, neither to install nor for daily work.

Do I have to train the speech recognition on my voice?

No. The recognition model works with any voice without training and detects 25 European languages automatically, including English and German. Names and technical terms it cannot know, such as clients, products or colleagues, you add once to the dictionary. After that they are always written the way you want them.

Can I dictate in Outlook and Word?

Yes, and without an add-in. Put the cursor in the email or document, hold the dictation key, speak and let go. The finished text is inserted at the cursor position, just as if you had typed it. SpeechToWork puts the greeting and the sign-off on lines of their own.

What happens if the AI misunderstands something?

A check compares the language model's output with the recognised text. If the result looks implausible, for example much longer than what you said or an answer instead of a tidy-up, SpeechToWork inserts the recognised raw text instead. So your dictation is never lost, and you can still correct it by hand.

Coming soon

Coming soon. Then try it for 14 days.

SpeechToWork is about to launch. As soon as the first version is ready, you can download it here: one click, one file, no form.

Coming soon

For Windows 10/11 (64-bit). The download will be available here as soon as it is ready.

  • All features, no payment details
  • Ends automatically, nothing to cancel
  • Your dictations never leave your computer, not even in the trial
  1. Download

    One installer for Windows, straight from our server.

  2. Install

    A double click is all it takes. No administrator rights needed.

  3. Choose “Try for 14 days”

    On first start: enter your name and business email, no payment method.

On first start, SpeechToWork downloads the language models once (4 to 6 GB). Already have a licence key? Enter it on first start. What is transferred in the process is explained in our privacy policy.

Coming soon