Free
A real, working file, built in minutes.
- Full 13-dimension conversation
- Your complete style profile
- Baseline anti-AI filter
- Markdown & text export
- Voiceprint ID, emailed to you
Signals listened for
~58
For people who write with AI every day
This is what your writing voice looks like.
Thirteenlivingdimensionsonevoicefile
Same brief, two answers below. One model reading nothing, the same model reading one voiceprint. Nothing else changed.
A real, working voiceprint. All 58 answers, each in its own place.
Build your voice, free
See how it works
- 12 min
- start to finished file
- 0 words
- of your own writing, ever
- No account
- no password — just an email, to send the file
- 14 days
- to change your mind, on paid files
13
Living dimensions
~12 min
To sound like you
Fingerprint a sample, yours will differ
7f3a·9c2e·d011
Banned by name in your file● anti-AI filter
delvetapestryseamlessit's not just X, it's Ythe rule of threeelevatea tidy bow at the endunlock
It happens to everyone who writes with AI for long enough.
The instruction slides up the context, and the writing goes back to default. The first few replies land close enough, so the guard comes down. Then the session gets long, the instruction sits further and further from where the model is reading, and the writing quietly returns to the house style every model shares.
Same brief, two answers
“Tell the people who follow you that you’re raising your prices.”
Switch between the two drafts — same brief, same reader, one voiceprint apart.
Hey everyone, I want to share a quick update regarding the newsletter. Starting next month, I'm going to be raising the subscription price from $5 to $8 a month.
When I first launched this project two years ago, my goal was to make it as accessible as possible. Since then, the scope of work and the depth of research I put into every issue have grown significantly. To keep delivering the quality, detailed essays you've come to expect—without taking on outside sponsors or compromising—adjusting the rate is a necessary step.
If you're already an active subscriber, your rate will stay locked in at the original price for the next six months as a thank you for your early support. Thank you so much for being part of this journey and making this work possible. If you have any questions or feedback, my inbox is always open.
Marked in red: a phrase our filter names as an AI tell. None of them is wrong. They are the shapes every model reaches for, which is why this draft reads like four other announcements the same reader saw this week.
- “I want to share a quick update”throat-clearing before the news
- “grown significantly”an intensifier that measures nothing
- “come to expect”stock phrase
- “—without taking on outside sponsors or compromising—”an em-dash aside doing no work
- “as a thank you”reflexive gratitude
- “Thank you so much”the same beat again, two sentences later
- “part of this journey”cliché
- “my inbox is always open”stock sign-off
8 named tells8 sentences12–29 words a sentence
Gemini 3.6 Flash, cold, one prompt, no system message. First response, unedited.
I’ve been putting off writing this note for a couple of weeks now, mostly because talking about money always feels a bit uncomfortable. But honestly, here's where I'm at.
Starting next month, I’m raising my rates.
Over the past two years, I’ve put a ton of energy into making sure every person I work with gets deep focus from me without feeling rushed. The dream has always been to deliver depth over volume. To keep doing that—and to give each of you the attention you actually deserve—I need to adjust the numbers.
If we’re already working together, your rate stays right where it is until we wrap up current work. New bookings after the 1st will reflect the new pricing.
I really appreciate you all for trusting the work. If you have questions about how this affects what we're doing, just hit reply.
0 named tells10 sentences6–28 words a sentence
Same brief, same model, same length — both drafts run to about 150 words, which is what A came to on its own. Gemini 3.6 Flash, one prompt, first response, unedited, and not picked from several attempts. The only thing added was one real voiceprint.
Read on its own, A seems fine. That is the whole problem. Nothing in it is wrong, and nothing in it is anyone. Eight tells in one short draft is the shape the reader has already seen four times this week, in four other announcements. B answers the same brief in the same number of words, gives the news a line of its own, and swings from six words to twenty-eight.
Everyone's AI sounds the same. Yours shouldn't.
Ask any model to write for you and it reaches for the middle of everything it has read. That middle is an average of millions of people, which is why the writing is recognisable and why it belongs to nobody in particular. A preset moves you to a different point on the same average.
A voiceprint pulls the other way. About fifty-eight small choices about how you actually write, kept as coordinates rather than adjectives, written down as one file a model can follow. It describes one writer. It fits the way a signature fits.
Add humanity back into your writing
The difference is measurable, so we measured it.
One brief, two answers, the same model on both sides. The only thing that changed was whether it was reading a voiceprint. Then we counted.
Sentence-length swing
0.3030.483
Coefficient of variation. 1.59× the swing, which is the movement a person’s sentences make when nobody is smoothing them out.
Shortest and longest sentence
12–296–28
Words. In the same total length, the voiced draft is willing to stop after six.
Named AI tells present
80
Eight phrases flagged in Exhibit A. In B there is nothing to flag.
Default model · 8 sentences, 12–29 wordsReading one voiceprint · 10 sentences, 6–28 words
Both drafts are real and unedited. The default one is a competent answer, which is exactly why it earns a place here.
Long stretches, short ones, and somebody deciding which
The same brief, written by three different people.
One awkward assignment, run through three real voiceprints. Same AI, same prompt. The only thing that changed was the voice file.
The brief
same for all
same for all
“Tell the people who follow you that you’re raising your prices.”
Maren OseiResponse 1 of 3
The newsletter goes to $9 a month on August 1. It’s been $5 since 2021.
The arithmetic is simple. Each issue takes about three days — sourcing the incident, reading the actual NTSB or coroner findings, then redrawing the load path until a non-engineer can see exactly where it failed. At $5 those days were subsidized by my consulting income. In practice I was paying to write this. That’s the failure mode of a hobby that quietly became a second job.
The issues don’t change. Same primary sources, same refusal to run anything I can’t verify against a real report. The back catalog is most of the argument for the new number anyway — read the Hyatt walkway teardown and tell me it was worth less than a coffee.
If $9 is more than it’s worth to you, the archive stays free. No countdown, no farewell discount. The price is just the price now.
Flat assertion, no apology. The em-dash is hers on purpose. She names the false-urgency move and refuses it out loud.
Theo ParkResponse 2 of 3
Three years ago I told you all this thing would take eighteen months. We can laugh about that one now.
So here’s where I’m at. The next build adds the co-op mode basically every email asks for, and doing it right means a small team — an animator and a second programmer — instead of me vanishing into a cave for another year. That’s money I don’t have yet. So the price is going up: $20 to $28 when the co-op patch ships this fall.
If you already own the game, you own all of it — every future update included, the way it was promised on day one. I’m not going to be the guy who quietly edits the promise after people already paid. The new price is for the folks who haven’t found us yet.
Honestly? I went back and forth on even telling you this early. It felt a little like asking permission… But you all funded a stranger’s weird dream about a fishing village that runs on the tides, and you’ve earned the unglamorous money stuff before anybody else does. More soon. Go check on your farm.
Opens on a story and lands the news after the context. Talks straight to “you all.” The trailing ellipsis and the admitted doubt are allowed here.
Nell MercerResponse 3 of 3
The subscription goes to $7 a month. Here’s the part where I’m supposed to apologize for that.
I’m not going to.
Look. You’ve sat through this dance a hundred times — the wounded little essay about tough decisions and the rising cost of doing what we love, performed in the key of a man who’s about to start recycling press releases. Spare me. Spare yourself.
Here’s the part nobody says out loud. I write five of these a week. I read the thing I’m angry about all the way through, in full, before I’m angry about it in public — which, in this business, now counts as eccentric. And I’ve never let a PR person buy a sentence. That’s time I sell to no one. Seven dollars buys it back.
If the column was worth your Tuesday at four, it’s worth it at seven, and you already know which. If it wasn’t, the door’s right there. It doesn’t lock behind you. I’d take a thousand readers who think I’m worth the money over ten thousand who resent the invoice.
A forty-word sentence between three-word jabs. She names the objection, then refuses it on its own line, and punches at the genre rather than the reader.
Thirteen living dimensions
D-01 — D-13
What we listen for, layer by layer.
Most tools stop at tone. Thirteen dimensions go further down: the shape of a sentence, the marks it ends on, how far you stand from a reader, whether you argue or tell a story. The last one is a filter that names the AI tells and strikes them.
D-01
PersonalityWho is doing the talking
PersonalityWho is doing the talkingD-02
InvolvementHow close you stand to the reader
InvolvementHow close you stand to the readerD-03
Sentence RhythmShort strikes, long breaths
Sentence RhythmShort strikes, long breathsD-04
VocabularyThe words you reach for without thinking
VocabularyThe words you reach for without thinkingD-05
PunctuationYour fingerprint in marks
PunctuationYour fingerprint in marksD-06
StructureHow a thought gets built
StructureHow a thought gets builtD-07
Humor & WitWhere the smile sits, if anywhere
Humor & WitWhere the smile sits, if anywhereD-08
Emotional RangeHow much of you reaches the page
Emotional RangeHow much of you reaches the pageD-09
NarrativeStory first, or analysis first
NarrativeStory first, or analysis firstD-10
PerspectiveThe seat you write from
PerspectiveThe seat you write fromD-11
ContrarianThe instinct to push back
ContrarianThe instinct to push backD-12
Cultural CompassThe references you steer by
Cultural CompassThe references you steer byD-13
Anti-AI FilterBanned by name in every file
Anti-AI FilterBanned by name in every fileWhere the questions come from.
We commissioned a deep-research review and tied every question to it: stylometry, Biber's analysis of how writing varies, the psycholinguistics of personality, and how language models actually choose words.
01
Stylometry
The throwaway words — the, of, upon — that give a writer away. Your fingerprint.
02
Biber's dials
Style as continuous coordinates: involved or informational, narrative or analytic.
03
Anti-AI filter
The tells — delve, the rule of three, tidy bows — banned by name in every file.
04
The voice file
One portable Markdown file, structured so your voice survives a long session.
First question to finished file
01
Name it
Tell us who the voice is for: you, or a brand you're building.
02
Talk it through
A guided conversation of about 58 quick, human choices. You are picking between real passages, not naming yourself in adjectives.
03
Watch it form
Your voice file builds in real time as you answer, closer to you with every choice.
04
Take it anywhere
Download one clean file and drop it into any AI that takes a system prompt.
Everything past tone
Six things you get, roughly in the order they matter.
Your writing stops being recognisable as AI
The file names the tells and bans them outright. Under that it carries the mechanics most tools never reach: sentence rhythm, punctuation habits, how much hedging survives an edit, the instinct to push back, and the distance you keep from a reader. Thirteen dimensions of it, where tone is only the first.
You never have to describe yourself
Nobody can name their own register in adjectives. So we ask you to choose between real passages instead, the way a friend learns your voice by reading you.
Nobody else can wear it
The profile is built from roughly 58 choices across thirteen dimensions, not picked from a list of presets. It describes one writer.
It follows you between tools
One Markdown file for ChatGPT, Claude, Gemini, Cursor, or anything that takes a system prompt. It travels with you rather than plugging into one tool, so nothing can quietly drop it.
It behaves in every room
Adapted variants for email, blog and social on Pro. The same voice, dressed for the context.
It keeps working after you pay
Pay once and own it. Free updates as the engine improves, and no subscription, no gates, no rented identity.
You leave with a file you can read.
Everything Timbrel learns becomes one portable, human-readable document, plus a fingerprint that's yours alone.
- Field
- Voice profile · 13 dimensions, ~58 signals
- Format
- Markdown (.md) & plain text — JSON on Pro
- Fingerprint
- 7f3a·9c2e·d011 unique, never reissued
- Works with
- ChatGPT · Claude · Gemini · Cursor · anything with a system prompt
your-voice.md● writing
# Voice Profile fingerprint: 7f3a·9c2e·d011 ## Personality core Warm, plainspoken, a little wry. Leads with a clear idea, then earns it. ## Sentence rhythm Short. Then a longer, breathing line that lets the thought settle. ## Humor Dry, sparing, never at the reader's expense. ## Don't - no corporate hedging - no exclamation points - never "delve" or "tapestry"
Pricing
Starter
Full
Pro
What twenty-nine dollars buys
Build a real, working voiceprint for nothing. Pay one time, never a subscription, when you want it to hold up over a long session.
Before the number, the honest comparison.
Nobody's stopping you from building this by hand. What's genuinely slow is the groundwork underneath it. Why we still think it's worth $29 to skip →
The number itself is small math: a few hours of your own time and some tokens, against twenty-nine dollars and a file that's already built.
Either way it comes out plain, editable Markdown, so tinkering stays on the table.
$29 once
The same voice, engineered to stay put.
- Everything in Starter
- Your personalized anti-AI filter
- Calibration passages you pick
- Drift re-anchor guardrails
- Protected signature phrases
- Free updates as the engine improves
$59 once
For pros writing across email, social and long-form.
- Everything in Full
- 5 context variants: email, blog, social, long-form & technical
- One voice, tuned for every room
- JSON export
Fourteen days, no questions asked
Live with the file. Put it in front of a long session and see whether the voice holds. If it doesn't do what we've said on this page, reply to your receipt inside fourteen days and we refund it in full, and you keep the file. The whole policy is two paragraphs long.
For one voice across a whole team, team plans are coming. Get in touch and we will tell you when.
Questions & hesitations
Questions people ask before they start.
Everything people ask before they build, including the one you're probably thinking.
Why can't I just build a voiceprint myself?
You can, and if you love to tinker, maybe you should. Writing the prompt is the quick part. The slow part is the research-grounded framework underneath it: which stylometric and psycholinguistic signals actually carry a voice, questions that surface them without asking anyone to describe themselves in adjectives, and an anti-AI filter that names the tells one at a time. That took us several weeks of reading and drafting.
Twenty-nine dollars is what it costs to skip that. Set it against a few hours of your own time plus the tokens, and the comparison is yours to make.
If the appeal is making it fully custom, the file you get is plain, editable Markdown. Take it and tweak it to your heart's content. We did the research scaffolding; you keep total control.
What exactly do I walk away with?
One portable voice file, plain Markdown (.md) and text, plus a unique voiceprint ID. Inside: your style across thirteen dimensions, written as plain instructions a model can follow, your personal anti-AI filter, and your protected signature phrases. You can read every line of it. Here's exactly how it's structured →
Do I have to share my writing?
No, and that surprises people. You never paste, upload, or type your own prose. Timbrel learns a voice from quick guided choices, mostly "which of these passages sounds more like you?", plus a couple of optional words you love or want banned. Nothing to write, nothing to hand over.
Which AI tools does it work with?
Any that take a system prompt or custom instructions: ChatGPT, Claude, Gemini, Cursor, and most of the rest. It's not a plugin or an integration; it's a file you bring with you, so it isn't locked to one platform.
How do I actually use it day to day?
Paste it once into the system prompt, custom-instructions, or "project" slot of whatever model you use. From then on it rides along on everything you write there, so you never have to paste it in again.
Will it actually sound like me, or just less generic?
Like you. It's measured: we map your style from the choices you make instead of asking you to describe yourself in adjectives. It captures your sentence-length swing (burstiness), your involved-or-informational lean, your punctuation habits, and the exact phrases you genuinely overuse, then bans the machine's defaults so they don't paper over yours. See three real voiceprints on the same brief →
Can I edit or customize it afterwards?
Completely. It's plain Markdown with nothing locked. Rewrite a line, add a rule, swap a protected phrase. It's yours to hack. Most people who live in AI tools want to tinker, and this is built to be tinkered with.
Do you store my writing or train models on it?
There's nothing to collect: you never hand us any writing. We store only your answers (the choices you made) and, if you give it, your email, used purely to generate and send your file. We don't train on anything and we don't sell it. Since there are no accounts, there's no profile of you sitting around to leak.
Do I need an account?
No account and no password. We do ask for an email at the end, and only for one reason: to send you a copy of the file so it isn't stranded in one browser. You see it on screen either way.
What's the difference between Free, $29 and $59?
Free gives you the full thirteen-dimension conversation, your complete style profile, and a generic baseline anti-AI filter. It sets your voice, and it genuinely works. Full ($29) keeps it there: your personalized anti-AI filter (your exact tells and pet peeves), the calibration passages you picked, your protected signature phrases, and the hard rules bracketed top and bottom that stop it drifting back to default over a long session. Pro ($59) adds five ready-to-use context variants, the same voice tuned for email, blog, social, long-form and technical writing. One-time, never a subscription. Compare the tiers →
How is this different from telling the AI to "write like me"?
A one-line "sound like me" gives the model nothing to measure, so it falls back on the same averaged defaults, and quietly forgets the instruction a few turns in. A voiceprint hands it actual coordinates and re-anchors them so they hold. Why "write like me" never quite works →
See what your
voice looks like.
Your voice is a fingerprint · build yours in about twelve minutes
