Starter
Free
A genuinely usable file that describes your voice. Built in minutes.
- Full 13-dimension conversation
- Your complete style profile
- Baseline anti-AI filter
- Markdown & text export
- Voiceprint ID — emailed to you
A voice that could only be yours
Make your AI sound unmistakably human.
A gentle, guided conversation maps how you actually write — across thirteen living dimensions — into one voice file you can drop into any AI. No two are alike.
1036
Possible voices
13
Living dimensions
~12min
To sound like you
The premise
Everyone's AI sounds the same. Yours shouldn't.
The big platforms hand you a few sliders and call it a "brand voice" — the same hundred presets recycled across millions of people. We don't give you a preset. We listen for the small choices that make your writing yours, and hand them back as a voice no one else can wear.
Thirteen living dimensions
One voice, mapped thirteen layers deep.
Most tools stop at tone. Timbrel listens for sentence rhythm, your punctuation fingerprint, the instinct to push back — then runs it through a filter that strips out the tells that make writing sound like AI.
Yourvoiceprint
How it works
Four steps. One voice. Infinite use.
Name it
Tell us who the voice is for — you, or a brand you're building.
Talk it through
A guided conversation — about 60 quick, human choices, not abstract sliders.
Watch it form
Your voice file builds in real time as you answer — see it become you.
Take it anywhere
Download one clean file and drop it into any AI that takes a system prompt.
What makes it different
Not another tone slider.
A deep, warm engine that listens for who you actually are as a writer — then hands it back to you.
Thirteen living dimensions
Beyond tone — sentence rhythm, punctuation fingerprint, the instinct to push back, and a filter that strips out the AI tells.
"Which sounds more like you?"
No abstract sliders — and nothing to write. You pick between writing samples we show you, the way a friend learns your voice.
A one-of-a-kind voiceprint
Your profile is a unique mark, like a fingerprint. Statistically, no one else will ever share it.
Drops into any AI
One clean markdown file for ChatGPT, Claude, Gemini, Cursor — anything that takes a system prompt.
One voice, many rooms
Adapted variants for email, blog, social — the same you, dressed for the context.
Yours to keep
Pay once and own your voice forever. No subscription, no gates, no rented identity.
What you walk away with
A voice file, not a vibe.
Everything Timbrel learns becomes one portable, human-readable document — and 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
# 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"
From early builders
What people do with their voice back.
“Quote goes here.”
“Quote goes here.”
“Quote goes here.”
Pricing
Start free. Upgrade once.
Build a real, working voiceprint for nothing. Pay one time — never a subscription — when you want the AI to actually obey it.
Full
$29 once
The file that makes the AI obey it — tuned to you alone.
- Everything in Starter
- Your personalized anti-AI filter
- Calibration passages you pick
- Drift re-anchor guardrails
- Protected signature phrases
Pro
$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
- Free updates as the engine improves
Building one voice for a whole team? Team plans are coming — get in touch.
Questions & hesitations
The honest answers.
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. But the part that takes real time isn't writing a prompt. It's building the research-grounded framework: working out which stylometric and psycholinguistic signals actually matter, the right questions to surface them without asking you to describe yourself in adjectives, and the anti-AI filter that names the tells and kills them. That's a few hours of reading and drafting, plus the tokens to get there.
So do the math honestly:
$29 ÷ (hours to build a fully-researched voiceprint − your token cost) = your effective hourly rate
If your time is worth more than that number, let us hand you the finished framework. And if the appeal is making it fully custom — remember 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 your 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 — no copying it back in each time.
Will it actually sound like me, or just less generic?
Like you. The difference is that it's measured, not described. 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. No accounts, so there's no profile of you sitting around to leak.
Do I need an account?
No. No sign-up, no password, no dashboard. You build your voice and leave with the file.
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 describes your voice, and it genuinely works. Full ($29) makes the AI obey it: your personalized anti-AI filter (your exact tells and pet peeves), the calibration passages you picked, and the hard rules bracketed top and bottom that keep it from drifting. 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 →
Ready to sound like nobody else?
Your voice is a fingerprint, not a preset. Build yours in a quiet quarter-hour.
Build your voice — free →