Day one lab · Level 0 · free
Hold a key, talk, get text. The first version takes about an hour, and honestly, anyone can ask an AI for one. What people pay for is everything stacked on top: the right models, running on your own computer, a style for every app, your phone, and a record of everything you've said. That's what you learn here, one layer at a time.
version 1 runs in Chrome or Edge. no python.
What the shops charge
| Wispr Flow | $15 / mo |
| Typeless | $30 / mo |
| Version 1, tonight | $0 |
| Version 3, Scribe, in the Lab | $0, forever |
Where it ends up · an illustration
Not the bare version: the one you end up with. It hears you in any app, writes the way that app needs, works from your phone, and keeps a record of everything you've said, so you can see how you actually talk.
Your notes, saved on this computer
Talk into your phone. Your own computer at home does the work and sends the text back. No subscription, no cloud.
An illustration, not a live demo. Words dictated, pace, hours saved and sessions are my real numbers from Scribe; the words, phrases and topics are examples of what the insights look like. Yes, "go ahead and" is mine.
How it gets better · layer by layer
Ask any AI for a voice-to-text tool and you'll have one in minutes. It works, and it's bare. Each layer below is a lesson, and each one makes the same tool better. That's the difference between a toy and something you'd pay for.
A button, your microphone, a speech service. Works in an hour. Your voice goes to someone else's server, and it's copy and paste from there.
Speech models come in sizes. Small ones are instant and miss names; big ones catch accents and jargon but want a graphics card. You'll test three on the same paragraph and pick yours.
Download the model once and your voice never leaves the machine. Free to run, works offline, and a hotkey types straight into any app.
Hearing words isn't understanding them. A language model fixes punctuation, drops the ums, turns "ten thirty" into 10:30 and keeps your meaning.
Casual in chat, professional in email, word for word in your code editor. Plus shorthand: say a short phrase, get the full thing typed out.
The mic stays open into a short memory buffer, so it rewinds a third of a second when you press the key. A small detail, and the one people notice most.
Every dictation saved on your computer and searchable. Then the fun part: your pace, the words you lean on, the phrases you repeat, what you talked about this week.
Put your phone and your computer on one private network with Tailscale. Talk into your phone; your computer at home does the work and sends the text back.
Speech to text. Bigger usually means more accurate and slower. Some are English only and very fast.
The clean-up step. Same text in, very different results, costs and privacy.
The bars are rough, to show the trade-off. In the lab you measure your own, on your own computer, with the same 100-word paragraph.
Version 1 · tonight · about an hour
You don't write code tonight. You describe the tool to an AI, save what it gives you as a file, open it, and paste any error back. That loop is the lesson. Use Claude, ChatGPT or Gemini; it doesn't matter which.
Copy this into your AI. Save the reply as dictate.html in a new folder. Open that folder in VS Code, install the free Live Server extension, and click Go Live at the bottom right. Your page opens at 127.0.0.1 in your browser; use Chrome or Edge.
Why not just double-click the file? Browsers only let speech recognition use your microphone on a real web address, and a file you double-clicked isn't one. 127.0.0.1 is a real address that lives on your own computer, so it counts.
If it doesn't work, paste the error message (or "the button does nothing") back to the AI and try again. Two or three rounds is normal.
Want to see the finished one first? Try mine: it runs right here in your browser. Stuck after three rounds? Download it and compare it with yours. The comments explain every part.
Make a free account at console.groq.com (no card) and create an API key. Then paste this to your AI. This is layers 2 and 4 in miniature: a better model to hear you, and a second model to understand you.
Now it works in any browser, the accuracy goes up, and you can see what clean-up costs in tokens.
Read the test paragraph below into your tool, count the wrong words, note the latency, and fill in the scorecard. You'll fill in the same scorecard for version 2 and version 3, and the difference will be yours.
The scorecard · fill it in before you leave
The test paragraph · 100 words · read it in one go, no pause before the first word
Hi, this is a quick test of my dictation tool. My name is Maya Patel and I work with Jordan Reyes on the Tuesday report. We ship about 240 orders a week, and the API that tracks them goes quiet around noon. Yesterday I said the first word too quickly and the tool missed it. Numbers like 3.5 and names like Okonkwo are the hard part. If this comes back with every word, the punctuation in the right place, and nothing invented, the tool is better than most. Stop recording right after the last word, with no pause at all.| Measure | How | Your version 1 | Version 3: Scribe (mine, measured) |
|---|---|---|---|
| Wrong words | out of the 100 in the paragraph | measured in the Lab, on the same paragraph | |
| Latency | seconds from release to text; your tool shows it | 0.92 s median | |
| Cost to run | per 1,000 words: the speech API's price plus clean-up tokens. Free tier = $0 today; write the list price | $0, runs on your computer | |
| Cost to build | tokens or dollars your AI used, from its usage screen | about 25,000 lines, with tests | |
| Where the voice went | cloud, or your computer | your computer, nothing leaves it | |
| First word survived? | did "Hi" come through | yes: the mic rewinds a third of a second | |
| Pace | words a minute while speaking | 160 wpm average, best session 245 | |
| Time saved so far | words spoken vs typing them at 40 wpm | 10.4 hours over 342 sessions |
Three versions of the same tool
Each version fills in the same scorecard, so you watch your own numbers move. Version 2 is free. Version 3 is the app I use every day, and the Lab builds it with you.
Why I built mine
When you talk to a chatbot, your ideas live in its history, on its servers, in its format. Dictation is different: you're producing your own notes all day, in your own words. Kept on your computer, they're searchable, they show you what you keep coming back to, and you get better at saying it.
That's what my stats page is: 77,000 words in a month, which apps they went to, how fast I talk, how much time it saved. Mine, measured, on my machine. Version 1 starts that tonight: the prompt in step 1 keeps your last 20 dictations.

Keep going · free
Leave your email and you'll get version 2 (the one that runs on your own computer), the nine-level roadmap, and a note when the Lab opens. You don't have to buy anything to keep building this. Run wild with it.