Dictation for Windows.
Free. Yours.
Wispr Flow raised 361 million dollars to rent you your own voice for 15 dollars a month. We put the same thing behind one key. Greek and English, everything on your PC, nothing in the cloud.
Every model is inside the file. No internet connection after setup. No account, no ads, no subscription, MIT license.
The numbers
Every figure in the left column is public. Ours are even easier to verify: they are zero.
| Wispr Flow | Fuck You Flow | |
|---|---|---|
| Price | 12 to 15 dollars a month | 0, forever |
| Company valuation | 2 billion dollars (August 2026) | One domain name |
| Investor money | 361 million dollars | One weekend |
| Where your voice goes | Their servers | Into the text. Then nowhere. |
| Account | Required | None |
| Internet | Always | Only to download it |
| Greek | One of 100+ languages | First language, mixed with English in the same sentence |
| Source code | Secret | Open, MIT, on GitHub |
The models that do Greek well have been open and free for two years. Someone had to put them behind a key. We did.Luram AI Agency, Thessaloniki
How it works
Three steps. In any program: Word, Chrome, Slack, Outlook, even a terminal.
Press right Alt
A small window with a waveform appears. It listens.
Speak
Greek, English or both. Each finished phrase is transcribed while you keep talking.
Press right Alt again
The text lands where your cursor was. With periods, commas and question marks.
Speed
Measured on an RTX 3070 with the large model. The wait runs from the moment you release the key to the text appearing.
| Words | Speech | Wait |
|---|---|---|
| 32 | 17.5 s | 0.59 s |
| 108 | 82 s | 0.17 s |
| 179 | 77 s | 0.53 s |
| 312 | 152 s | 0.88 s |
The wait depends only on the length of the last phrase, because the earlier ones were transcribed while you spoke. On an AMD or Intel card the engine runs through Vulkan at the same speed. Without a graphics card it runs on the processor, with a wait of a few seconds.
What is inside
Everything the others sell as premium.
Greek that holds up
Question marks from the wording through grammar rules, or from the rise of your voice. Your spoken self-corrections are applied.
A dictionary that learns
Correct a word once in History and it becomes a rule. Names, companies and technical terms come out right from then on.
Every graphics card
NVIDIA, AMD, Intel. The first start reads the machine and picks the model and settings by itself.
Snippets
Say a phrase, get a whole block of text. Signatures, addresses, the replies you type every day.
History and statistics
How many words, how much time saved, what you said yesterday. All in one file on your disk.
Nothing leaves
No server, no analytics, no account. Password fields are detected and stay empty.
The app
Black, monospace, large type. Every screen is a list of facts.




FAQ
Is it a free alternative to Wispr Flow?
Yes. It does the same job, one-key dictation into any Windows program, with no subscription and no account. The code is open source under the MIT license on GitHub.
Where does my voice go?
Nowhere. Recognition runs on your own machine with the Whisper model. After setup no internet connection is needed. Password fields are detected and left empty.
Does it need an NVIDIA card?
No. The engine runs on NVIDIA, AMD and Intel cards through Vulkan. With no graphics card it runs on the processor, more slowly.
Why does Windows show a blue warning during install?
The installer carries no purchased code-signing certificate. Click "More info", then "Run anyway". The SHA256 checksum of the file is published on GitHub.
What does 0.9 beta mean?
It runs daily on our machines and is now going out to yours. Some programs may refuse the paste, some cards are untested. Whatever breaks, we want it written down.
Why the name?
A dictation company was valued at 2 billion dollars for something open models have done for free for two years. The name is the reply. On social media we write FU Flow.
Feedback
It is a beta. What broke, what you missed, what you liked, here.
Something broke
Tell us the program, the graphics card and what you saw. The Diagnostics tab in the app has "Recent problems" ready to copy.