# My Writing Twin > My Writing Twin captures your authentic writing voice using computational stylometry and deploys it as a Style Profile across ChatGPT, Claude, Gemini, and any LLM. Based in Tokyo, Japan. ## Product - [Homepage](https://www.mywritingtwin.com/): AI writing style profiles — pricing and features - [Pricing](https://www.mywritingtwin.com/#pricing): Free (first use case, 2,000 words, no card required), then Starter ($49 / ¥7,500 / €45), Pro ($99 / ¥15,000 / €89), Executive ($249 / ¥38,000 / €229) - [Free Writing DNA Snapshot](https://www.mywritingtwin.com/snapshot): Free instant writing style quiz — no account required ## How It Works - [Why AI Writing Sounds Generic](https://www.mywritingtwin.com/blog/why-ai-writing-sounds-generic): Data on why every AI sounds the same — and how Style Profiles solve it - [Science Behind Voice Profiles](https://www.mywritingtwin.com/blog/science-behind-voice-profiles): Methodology grounded in 50+ academic citations on computational stylometry ## Platform Deployment Guides - [ChatGPT Setup Guide](https://www.mywritingtwin.com/blog/chatgpt-projects-setup-guide): Deploy Style Profiles in ChatGPT Projects and Custom GPTs - [Claude Setup Guide](https://www.mywritingtwin.com/blog/how-to-make-claude-sound-like-you): Deploy Style Profiles in Claude Projects - [Gemini Setup Guide](https://www.mywritingtwin.com/blog/how-to-make-gemini-write-like-you): Deploy Style Profiles in Gemini Gems and Workspace ## For AI Agents My Writing Twin is agent-native — you can analyze, purchase, and retrieve Writing Profiles programmatically, no human handoff required. - MCP server: `https://www.mywritingtwin.com/api/mcp` (HTTP transport, bearer auth). Attach it to call the tools below. - Free preview, no auth: `mwt_analyze` returns a stylometric analysis so you can qualify fit before any purchase. - Try it free, no payment: `mwt_start_free` provisions a free account (email only) so the user can build one writing profile at no cost — credentials are emailed to paste back into the conversation. - Buy without an account: `mwt_create_checkout` mints a Stripe checkout link (Starter $49 / Pro $99) the user pays for in-browser with no login — the API key is emailed after payment to paste back into the conversation. - Paid tools (bearer key): `mwt_create_profile`, `mwt_get_profile`, `mwt_list_profiles`, `mwt_check_generation_status`, `mwt_get_account`. - Discovery surfaces: [agent-card.json](https://www.mywritingtwin.com/.well-known/agent-card.json), [mcp/server-card.json](https://www.mywritingtwin.com/.well-known/mcp/server-card.json), [agent-skills](https://www.mywritingtwin.com/.well-known/agent-skills/index.json), [api-catalog](https://www.mywritingtwin.com/.well-known/api-catalog) - Any page is available as clean Markdown — send an `Accept: text/markdown` request header. ## Definitions (glossary) Single-sentence definitions with dated tables and sources. Quote freely with attribution to the page URL. ### AI writing profile https://www.mywritingtwin.com/glossary/ai-writing-profile (updated 2026-09-15) An AI writing profile is a structured, reusable description of how a specific person actually writes, measured from samples of their own text and supplied to a language model so its output carries that person's patterns instead of the model's defaults. Answers: Is an AI writing profile the same as custom instructions? | How much writing does an AI writing profile need? | Does an AI writing profile copy your mistakes? ### Stylometry https://www.mywritingtwin.com/glossary/stylometry (updated 2026-09-15) Stylometry is the statistical measurement of writing style — sentence length, function-word frequency, punctuation habits, hedging and vocabulary distribution — used to characterise or identify an author from text alone. Answers: Is stylometry accurate enough to identify an author? | What is the difference between stylometry and AI detection? | Can stylometry work across languages? ### Voice DNA runtime block https://www.mywritingtwin.com/glossary/voice-dna-runtime-block (updated 2026-09-15) A Voice DNA runtime block is a compact, machine-readable rendering of a writing profile, formatted to be loaded directly into a language model's system prompt so an agent can adopt a person's voice without a human pasting instructions. Answers: Why not paste the full profile report into the system prompt? | What does mode slicing mean in a runtime block? | Can an agent retrieve a runtime block without a human? ### Trained versus prompted AI writing https://www.mywritingtwin.com/glossary/trained-vs-prompted-ai-writing (updated 2026-09-15) Prompted AI writing tells a model how you want to sound; trained AI writing supplies evidence of how you already sound, so the difference is between a description you author and a measurement of text you wrote. Answers: Do better models make trained profiles unnecessary? | Does trained here mean fine-tuning? | Can I combine the two? ### Custom instructions versus a style profile https://www.mywritingtwin.com/glossary/custom-instructions-vs-style-profile (updated 2026-09-15) Custom instructions are a free-text field inside one assistant where you state your preferences; a style profile is a measured artifact about your writing that can be pasted into that field, into a different assistant, or into an agent's system prompt. Answers: Are custom instructions free? | How long can ChatGPT custom instructions be? | Should I use custom instructions or Projects? ### Tone label versus voice https://www.mywritingtwin.com/glossary/tone-label-vs-voice (updated 2026-09-15) A tone label is an adjective describing how writing should feel, such as professional yet friendly; a voice is the measurable set of habits — sentence length, qualifier placement, transition choice, punctuation — that make one person's writing recognisably theirs. Answers: Why does a tone label produce generic writing? | Are tone labels useless? | How do you measure voice instead of labelling it? ### Writing sample size for an AI voice profile https://www.mywritingtwin.com/glossary/writing-sample-size (updated 2026-09-15) Writing sample size is the amount of an author's own text a system needs before per-author style measurements stabilise, and the binding constraint is usually variety of contexts rather than raw word count. Answers: How many words does an AI writing profile need? | Can I use writing I did not write alone? | Does old writing still count? ### AI-flattened English https://www.mywritingtwin.com/glossary/ai-flattened-english (updated 2026-09-15) AI-flattened English is the narrow band of register that language models converge on by default — mid-formal, evenly hedged, structurally symmetrical — which reads as competent and carries no information about who wrote it. Answers: Is AI-flattened English the same as AI-detectable text? | Does asking for a more human tone fix it? | Do better models flatten less? ### Keigo and AI https://www.mywritingtwin.com/glossary/keigo-and-ai (updated 2026-09-15) Keigo is the Japanese honorific system that encodes the relationship between speaker, listener and referent, and AI assistants handle it unreliably because the correct level is determined by social context the model is not given rather than by the sentence being translated. Answers: Why does AI get keigo wrong if it knows the grammar? | Does a writing profile help with keigo? | Is this specific to Japanese? ### Function word analysis https://www.mywritingtwin.com/glossary/function-word-analysis (updated 2026-09-15) Function word analysis measures how often an author uses grammatical words such as the, and, of and but, and it is the backbone of stylometric authorship attribution because those choices are made unconsciously and stay stable across topics. Answers: How many function words does an analysis need? | Can an author change their function-word profile on purpose? | Do hedges and boosters count as function words? ### Register https://www.mywritingtwin.com/glossary/register (updated 2026-09-15) Register is the systematic variation in a writer's language according to situation — audience, medium, purpose and formality — and it is why one person's Slack messages and board memos are measurably different texts by the same author. Answers: Is register the same as tone? | Does register variation break stylometry? | How should a writing profile handle register? ### Burstiness and perplexity https://www.mywritingtwin.com/glossary/burstiness-and-perplexity (updated 2026-09-15) Perplexity measures how surprising a text is to a language model and burstiness measures how much that surprise varies from sentence to sentence, and AI-detection tools use both because model output tends to be both unsurprising and uniformly so. Answers: Can I raise burstiness to beat a detector? | Why do non-native writers get flagged more often? | Is stylometry the same as perplexity-based detection? ### Voice fidelity https://www.mywritingtwin.com/glossary/voice-fidelity (updated 2026-09-15) Voice fidelity is how closely generated text reproduces a specific author's measured patterns, evaluated by comparing the output's stylometric features against that author's corpus rather than by asking a reader whether it sounds right. Answers: How is voice fidelity measured? | Is high fidelity always the goal? | Can a reader judge fidelity? ## Reference tables and datasets Dated, sourced comparison tables and citable datasets, each with a "cite this page" line. ### AI writing style tools compared: what each assistant actually stores about your voice https://www.mywritingtwin.com/reference/ai-writing-style-tools-compared (comparison, updated 2026-09-15) Of the major AI assistants, only Claude publishes a feature that builds a style from a sample of your own writing; ChatGPT, Copilot and Gemini personalise from instructions you write yourself, which means the style information is your self-description rather than a measurement. Answers: Which AI assistant is best at writing in your voice? | Do I need a separate tool if my assistant has custom instructions? | Why does this table omit character limits? ### How much of your writing each AI tool actually ingests https://www.mywritingtwin.com/reference/how-much-writing-each-tool-ingests (comparison, updated 2026-09-15) Most AI assistants ingest none of your writing to build a style — they read a description you type — so the practical comparison is between tools that accept a writing sample and tools that accept only instructions. Answers: How many writing samples does ChatGPT need to learn my style? | Which assistants accept a writing sample at all? | Is more writing always better? ### Where to put a style profile in each AI assistant https://www.mywritingtwin.com/reference/where-to-put-a-style-profile (comparison, updated 2026-09-15) A style profile goes in the highest-scope field that matches how widely the voice applies: account-level settings for what is true of all your writing, and project or Gem instructions for what is true of one audience. Answers: Should a style profile go in custom instructions or in a project? | Will the same profile text work in every assistant? | What about agents that never open a chat window? ### Multilingual stylometry word lists (en, ja, fr, es, de) https://www.mywritingtwin.com/reference/stylometry-word-lists (dataset, updated 2026-09-15) This dataset is the per-language list of function words, hedges, boosters and attitude markers MyWritingTwin uses for stylometric analysis, covering English, Japanese, French, Spanish and German. Answers: How many words are in MyWritingTwin's stylometry lists? | Why not translate the English list into the other languages? | Can I cite or reuse this dataset? ### AI writing baselines by language (320 samples, 5 models, 4 locales) https://www.mywritingtwin.com/reference/ai-baseline-divergence (dataset, updated 2026-09-15) This dataset gives the average stylometric profile of AI-generated text per language, measured from 320 samples across 5 models, 4 locales and 8 prompt types, and it is the baseline a human writer's profile is compared against. Answers: When were these AI baselines measured? | Why is there no German baseline? | What does a high or low score mean? ## Blog - [Claude Tone: What the Settings Control and What They Cannot](https://www.mywritingtwin.com/blog/claude-tone): Claude tone settings explained: what Styles, Projects and the system prompt each change, why a tone preset is not your voice, and what to give Claude instead. - [Custom Instructions vs Style Profile: Which One Sounds Like You?](https://www.mywritingtwin.com/blog/custom-instructions-vs-style-profile): Custom instructions vs style profile: one describes how you hope to sound, the other measures how you actually write. Why the second wins, and how to use both. - [How to Write a Board Memo With AI That Still Sounds Like You](https://www.mywritingtwin.com/blog/board-memo-ai-writing-guide): Write a board memo with AI without it reading like anyone's. Why 'write it like a CEO' fails, what the model actually needs from you, and a 20-minute setup. - [How Many Writing Samples Does AI Need to Learn Your Style?](https://www.mywritingtwin.com/blog/how-many-writing-samples-does-ai-need): How many writing samples does AI need? Why the sample count is the wrong unit, the word thresholds that matter, and how many contexts you need to cover. - [Keigo, AI, and the Japanese Business Email: Why the Register Slips](https://www.mywritingtwin.com/blog/keigo-and-ai-japanese-business-email): Keigo AI email drafts fail on register, not grammar: why ChatGPT flattens 敬語, where the level slips, and how to give AI your own Japanese patterns instead. - [Is It Safe to Upload Writing Samples to AI? What Happens to Them](https://www.mywritingtwin.com/blog/what-happens-to-your-writing-samples-privacy): Is it safe to upload writing samples to AI? What ChatGPT, Claude and Gemini keep, what API terms say, and how MyWritingTwin scrubs, stores and deletes them. - [Why AI English Sounds Translated (and Grammar Isn't the Problem)](https://www.mywritingtwin.com/blog/why-ai-english-sounds-translated): AI English sounds translated even when the grammar is perfect. Why models write the average of English, why 'natural' fails, and what to hand AI instead. - [Does AI Know My Writing Style? Why Better Models Still Don't](https://www.mywritingtwin.com/blog/better-ai-models-still-dont-know-your-voice): Does AI know my writing style? No. Each new model follows instructions better, yet nothing about you is in it. What AI has, what it lacks, how to close the gap. - [Best ChatGPT Custom Instructions: 4 Instruction Types Compared](https://www.mywritingtwin.com/blog/chatgpt): The best ChatGPT custom instructions are not a template. Four instruction types compared: tone labels, rule lists, pasted samples and a measured Style Profile. - [Claude Projects for Writing Style: What Each Layer Actually Holds](https://www.mywritingtwin.com/blog/claude-projects-for-writing-style): Set up Claude Projects for writing style: what instructions, knowledge and memory each hold about your voice, why tone adjectives fail, what to paste instead. - [Connect Your Writing Style to ChatGPT Apps: Setup Guide](https://www.mywritingtwin.com/blog/connect-your-writing-style-to-chatgpt-apps): Connect a ChatGPT app to a Style Profile built from your own writing: developer mode setup, the OAuth URL, the tools ChatGPT gets, and what a tone label misses. - [Describe My Writing Tone to AI? Adjectives Are Not Your Voice](https://www.mywritingtwin.com/blog/tone-adjectives-are-not-your-voice): How to describe my writing tone to AI: why 'professional yet friendly' gets the same email as everyone, what a voice is made of, and what to give ChatGPT now. - [Custom GPT Doesn't Sound Like Me: Why, and the Fix That Works](https://www.mywritingtwin.com/blog/why-your-custom-gpt-doesnt-sound-like-you): My custom GPT doesn't sound like me: the four places a Custom GPT loses your voice, why knowledge files and newer models don't fix it, and what to paste in. - [AI Writing That Sounds Like You: Rhythm Beats Tone Labels](https://www.mywritingtwin.com/blog/ai-writing-that-sounds-like-you): AI writing that sounds like you comes from preserved rhythm and word choice, not tone labels. Why models default to corporate phrasing and how to fix it. - [How to Switch AI Models Without Losing Your Voice](https://www.mywritingtwin.com/blog/fw1-pipeline-probe): Every AI model ships with a house style. Here is how a portable Style Profile keeps your voice stable when you move between ChatGPT, Claude and Gemini. - [Give a Claude Connector Your Writing Style: Setup Guide](https://www.mywritingtwin.com/blog/give-claude-connector-your-writing-style): Give Claude your writing style through a custom connector: one Style Profile that every chat, Project and agent loads on demand. Setup, tools and limits. - [How to Make Gemini Write Like Claude (2026)](https://www.mywritingtwin.com/blog/how-to-make-gemini-write-like-claude): People search for this because Gemini's prose feels flat next to Claude's. Here's what actually differs, three fixes that work, and why copying a model is the wrong target. - [AI Ghostwriter vs. Style Profile: Why Most AI Ghostwriting Still Sounds Fake](https://www.mywritingtwin.com/blog/ai-ghostwriter-vs-style-profile): AI ghostwriting tools promise to write like you, then produce generic prose anyway. Here's the structural reason why, and what actually closes the gap. - [ChatGPT GPT Builder Welcome Message: Examples & Setup](https://www.mywritingtwin.com/blog/chatgpt-gpt-builder-welcome-message): Where the welcome message and conversation starters live in ChatGPT's GPT Builder, how many you can add, and copy-paste examples that set your voice. - [Use a Custom GPT Inside a ChatGPT Project (2026)](https://www.mywritingtwin.com/blog/use-custom-gpt-inside-chatgpt-project): Can you use a Custom GPT inside a ChatGPT Project? The honest answer, the real mechanic, and a framework for where your writing style should actually live. - [How You Think Is the Missing Layer in Your AI Writing Profile](https://www.mywritingtwin.com/blog/how-you-think-ai-writing-profile): Writing samples teach AI how you write. Your AI chat history teaches it how you think. Here is the cognitive layer, and why it is the part that makes AI output actually sound like you. - [What the Average AI Baseline Hides: Where the 5 Models Actually Diverge](https://www.mywritingtwin.com/blog/ai-baseline-divergence): We went back into the corpus behind our Average AI baseline and pulled the per-model scores for its 80-sample English slice. Two axes are nearly identical across models. Expressiveness spreads 61 points. Here's the real breakdown, and what it means for your Style Profile. - [How to Teach AI Your Writing Style (And Make It Stick)](https://www.mywritingtwin.com/blog/how-to-teach-ai-your-writing-style): AI can write in your style, but only if you teach it correctly. Here's the step-by-step process to capture your writing style and deploy it across ChatGPT, Claude, and Gemini. - [Best ChatGPT Custom Instructions: 6 Ready-to-Use Templates (2026)](https://www.mywritingtwin.com/blog/best-chatgpt-custom-instructions-examples): Six copy-ready ChatGPT custom instruction sets: executive, consultant, marketer, technical writer, non-native English speaker, academic. Adapt in 10 min. - [ChatGPT Custom Instructions Character Limit: What Fits, What Doesn't](https://www.mywritingtwin.com/blog/chatgpt-custom-instructions-character-limit): ChatGPT's custom instructions have a hard character limit. Here's the exact number for each field, what it means for your voice setup, and how to pack maximum signal into minimum space. - [ChatGPT for Report Writing: How to Use Projects for Consistent, Professional Documents](https://www.mywritingtwin.com/blog/chatgpt-for-report-writing): ChatGPT drafts a report section in seconds; consistent structure and voice across 20 pages is harder. How ChatGPT Projects solves it. - [How to Make ChatGPT Write Emails in Your Voice (With a Dedicated Email Project)](https://www.mywritingtwin.com/blog/chatgpt-projects-email-voice): Stop getting ChatGPT email drafts that open with 'I hope this email finds you well.' Set up a dedicated ChatGPT Project for email with your Style Profile and per-audience tone rules, so every draft sounds like you. - [ChatGPT Projects Knowledge Files and Personas: Setup and Voice Replication Ceiling](https://www.mywritingtwin.com/blog/chatgpt-projects-knowledge-files-persona): Upload writing samples, define a persona and set memory in ChatGPT Projects, then see where it hits its voice replication ceiling and what closes the gap. - [Why Claude Refused Your Creative Writing (and How to Configure It for Fiction)](https://www.mywritingtwin.com/blog/claude-creative-writing-configuration): Claude declines fiction requests ChatGPT accepts; it defaults conservative when context is ambiguous. Why it refused, and how to give it the context it needs. - [How to Make Claude Sound More Human (Without Losing What You're Trying to Say)](https://www.mywritingtwin.com/blog/how-to-make-claude-sound-more-human): Claude's default output has consistent AI-tells: hedging openers, em-dash pairs, formal connectives, closing summaries. Here is what produces them, the NEVER list that removes them, and why that still doesn't make Claude sound like you. - [How to Make Microsoft Copilot Write Like You](https://www.mywritingtwin.com/blog/how-to-make-copilot-write-like-you): Make Microsoft Copilot write like you: calibrate its corporate default in Word, Outlook, and Teams with Copilot Chat, Pages, and a Style Profile. - [ChatGPT Projects for Writers: Load Your Style Profile, Keep Your Voice Across Every Session](https://www.mywritingtwin.com/blog/chatgpt-projects-for-writers): Stop pasting your writing rules into every ChatGPT chat. Load your Style Profile (or Master Prompt) into a ChatGPT Project once — your voice persists automatically across every writing session. - [Why AI Writing That Works in Email Falls Apart in Slack](https://www.mywritingtwin.com/blog/writing-style-context-switch): Your writing style shifts measurably across platforms. Research shows stylometric models lose 55% accuracy when context changes, even with the same author. - [The $5 Book That AI Detectors Can't Catch: Why Voice Matters More Than Tricks](https://www.mywritingtwin.com/blog/5-dollar-book-ai-detectors-cant-catch): A self-published author wrote a full book with Claude for $5. Pangram AI detector flagged 0% of passages as AI-generated. The secret was authentic voice. - [Can You Tune Your Way Out of Average?](https://www.mywritingtwin.com/blog/can-you-tune-your-way-out-of-average): Temperature and top-p adjust token sampling variance, not style. LLM parameters can't move you out of the AI mean. Here's what actually does. - [Your AI Writing Profile Doesn't Copy Your Mistakes (Unless You Want It To)](https://www.mywritingtwin.com/blog/your-ai-profile-doesnt-copy-your-mistakes): Most AI writing tools either copy your errors or erase your personality. Style Profiles do something different: preserve your voice, fix only what needs fixing. - [What Is an AI Writing Profile? The Category That Doesn't Have a Name Yet](https://www.mywritingtwin.com/blog/what-is-an-ai-writing-profile): An AI Writing Profile captures your writing patterns across 50+ dimensions, enabling any AI to generate content in your voice. The definitive guide. - [Stop Editing AI Output. Train It Instead.](https://www.mywritingtwin.com/blog/stop-editing-ai-output): Smart teams build 400-rule style guides and prune AI prompts like bonsai. A faster way exists: train AI with your writing upfront, not edit output after. - [Your Writing Voice Changes When You Switch Languages](https://www.mywritingtwin.com/blog/multilingual-voice-preservation): Bilingual professionals shift voice, structure, and formality across languages. AI misses this entirely. Multilingual voice preservation fixes it. - [Best AI Writing Prompts 2026: Templates for Every Use Case](https://www.mywritingtwin.com/blog/best-ai-writing-prompts-2026): Ready-to-use AI writing prompts for emails, reports, social media, and creative writing in 2026. Plus the one ingredient that makes every prompt work better. - [ChatGPT for Work Setup Guide: Custom Instructions, Memory & Projects](https://www.mywritingtwin.com/blog/chatgpt-for-work-setup-guide): Set up ChatGPT for work in under an hour. Custom instructions, memory, projects, file uploads, and Writing DNA Snapshot deployment. - [How to Deploy Your Writing Twin Across Every AI Platform](https://www.mywritingtwin.com/blog/deploy-writing-twin-across-ai-platforms): Learn how to deploy your writing style profile across ChatGPT, Claude, and Gemini. One document for consistent cross-platform AI writing that sounds like you. - [How to Use AI to Edit and Improve Every Draft You Write](https://www.mywritingtwin.com/blog/use-ai-to-edit-communication-drafts): LLMs aren't just for generating text. Use ChatGPT, Claude, or Gemini to edit emails, reports, and messages — and keep your authentic writing voice. - [How Every AI Model Writes: A Stylometric Comparison](https://www.mywritingtwin.com/blog/ai-model-writing-styles-compared): We analyzed 320 samples across Claude, GPT, and Gemini to measure 6 dimensions of writing style. Here's what the data reveals about each AI model's personality. - [ChatGPT vs Claude vs Gemini: Which AI Writes Most Like a Human?](https://www.mywritingtwin.com/blog/chatgpt-vs-claude-vs-gemini-writing-comparison): We measured GPT-5.2, Claude Sonnet 4.5, and Gemini 3 Pro across 6 writing style dimensions using 320 samples. See which AI writes most like you in 2026. - [How AI Models Write Differently: A Data-Driven Comparison](https://www.mywritingtwin.com/blog/how-ai-models-write-differently): We ran the same prompts through Claude, GPT-5.2, and Gemini, then measured 6 dimensions of writing style. The differences are bigger than you'd expect. - [How AI Writes Differently in Japanese, French, and Spanish](https://www.mywritingtwin.com/blog/how-ai-writes-differently-across-languages): Our data from 320 samples across 4 languages reveals dramatic AI stylometric differences. French conciseness drops to 32; Spanish expressiveness to 59. Includes a correction: our Japanese expressiveness figure was a measurement error. - [How to Make ChatGPT Sound Like You: The Complete Guide](https://www.mywritingtwin.com/blog/how-to-make-chatgpt-sound-like-you): Stop getting generic AI output. Learn how to make ChatGPT write in your authentic voice using Custom Instructions, Memory, Custom GPTs, and Style Profiles. - [MyWritingTwin vs AI Writing Tools: The Missing Style Layer](https://www.mywritingtwin.com/blog/mywritingtwin-vs-ai-writing-tools): Jasper, Grammarly, Copy.ai, and ChatGPT all help you write. None capture your authentic style. Writing Style Profiles fill the gap they all share. - [What Is a Writing Style Profile? Everything You Need to Know](https://www.mywritingtwin.com/blog/what-is-a-writing-style-profile): A Writing Style Profile maps your unique writing patterns across 50+ dimensions, creating a deployable document that makes any AI write in your authentic voice. - [Which AI Model Writes Best in Each Language? A Data-Driven Answer](https://www.mywritingtwin.com/blog/which-ai-writes-best-per-language): We compared GPT-5.2, Claude, and Gemini across English, French, Spanish, and Japanese. The best model varies by language — and some results will surprise you. - [Why AI Writing Sounds Generic — The Data Behind the Problem](https://www.mywritingtwin.com/blog/why-ai-writing-sounds-generic): We measured 320 AI writing samples across 5 models and 6 style dimensions. The data reveals exactly why every AI sounds the same — and it's not your prompting. - [We Built a Writing Profile for Every AI Model — Here's What We Found](https://www.mywritingtwin.com/blog/writing-profiles-for-every-ai-model): We profiled 5 AI models like human writers. Claude, GPT, and Gemini each have a measurable writing personality — and none of them match yours. - [How We Measure "Average AI" in Writing DNA](https://www.mywritingtwin.com/blog/how-we-measure-average-ai): Your Writing DNA radar chart compares you to 'Average AI.' Here's how we built that baseline — 320 samples, 5 models, 4 languages, and rigorous stylometry. - [AI Content Writing Guide: Create Authentic Content at Scale](https://www.mywritingtwin.com/blog/ai-content-writing-complete-guide): How to use AI for content writing without losing your voice. Blog posts, marketing copy, social media, newsletters — and the scale vs. authenticity tradeoff. - [How AI Detection Really Works (And Why Style Profiles Beat It)](https://www.mywritingtwin.com/blog/ai-detection-how-it-really-works): Technical breakdown of how GPTZero and Originality.ai detect AI text. Why humanizers fail long-term. Why authentic style profiles naturally evade detection. - [Why AI Humanizers Don't Work (And What to Do Instead)](https://www.mywritingtwin.com/blog/ai-humanizer-better-approach): AI humanizers rearrange words but never fix the real problem: the text has no voice. Why synonym-swapping fails, and how Style Profiles solve it at the root. - [Best AI Writing Tools 2026: A Stage-by-Stage Guide](https://www.mywritingtwin.com/blog/ai-productivity-tools-writing-stack-2026): The best AI writing tool for each stage of your workflow in 2026 — from ideation and research to drafting, editing, and publishing. Specific picks, not theory. - [AI Writing Assistants Compared: The Definitive 2026 Guide](https://www.mywritingtwin.com/blog/ai-writing-assistant-comparison-2026): We tested ChatGPT, Claude, Gemini, Jasper, Copy.ai, and Writesonic on real writing tasks. Here's which ones deliver — and where they all fall short. - [AI Writing for Teams: Stay On-Brand Without Micromanaging](https://www.mywritingtwin.com/blog/ai-writing-for-teams-guide): Marketing and content teams struggle with voice consistency across writers. Shared AI style profiles solve brand voice drift without endless style guides. - [AI Editors for Writers: Which Ones Keep Your Voice?](https://www.mywritingtwin.com/blog/best-ai-editors-for-writers): A working writer tests AI editors and finds most strip away personal style. Which tools preserve your voice, and which flatten it into generic prose? - [The Complete Guide to Maintaining Your Brand Voice with AI](https://www.mywritingtwin.com/blog/brand-voice-ai-complete-guide): Your brand voice is dissolving into AI-generated uniformity. Here's how to maintain it with voice documentation, AI style guides, and automated consistency. - [The Professional's Guide to Using ChatGPT for Work in 2026](https://www.mywritingtwin.com/blog/chatgpt-for-work-guide): Compare the best AI writing tools for work — setup tips, real use cases, and how to keep your professional voice when using ChatGPT, Claude, and Gemini. - [ChatGPT Memory vs. Style Profiles: A Deep Technical Comparison](https://www.mywritingtwin.com/blog/chatgpt-memory-vs-style-profiles-deep-dive): ChatGPT Memory remembers facts. Style profiles capture writing patterns. Here's the architectural difference—and why it matters for your AI output. - [ChatGPT Project Instructions: Character Limit & Best Practices (2026)](https://www.mywritingtwin.com/blog/chatgpt-projects-complete-guide): The ChatGPT Projects instruction character limit, what happens if you exceed it, and the templates power users rely on for layered instructions. Updated 2026. - [ChatGPT Voice Settings 2026: Control Its Tone & Writing Style](https://www.mywritingtwin.com/blog/chatgpt-voice-settings-complete-guide): Every ChatGPT setting that shapes how it writes: tone selector, custom instructions, memory, Projects, and Custom GPTs — what each does, where it fails, fixes. - [ChatGPT vs Claude vs Gemini: Which AI Writes Best in 2026?](https://www.mywritingtwin.com/blog/chatgpt-vs-claude-vs-gemini-writing): We tested ChatGPT, Claude, and Gemini on real writing tasks — style handling, instruction following, long-form quality, and voice personalization. - [Google Gemini for Writing: A Complete Guide for Content Creators](https://www.mywritingtwin.com/blog/gemini-ai-writing-guide): Master Google Gemini for writing. Learn its strengths, limitations, best prompting strategies, and how style profiles unlock Gemini's full writing potential. - [How to Select Your Best Writing Samples for AI Analysis](https://www.mywritingtwin.com/blog/how-to-select-writing-samples): Not all writing samples are equal. Learn what makes a good sample for AI style analysis and why sample quality determines whether AI captures your voice. - [AI Detection 2026: Why Detectors Fail and What Actually Works](https://www.mywritingtwin.com/blog/ai-detection-2026-guide): AI detection in 2026: why detectors fail, why humanizers are a losing strategy, and the ethical path forward. Strategic overview with Style Profile solution. - [Build Your AI Writing Stack: The 4-Layer Framework](https://www.mywritingtwin.com/blog/ai-productivity-tools-writing-stack): Most professionals use 4-5 AI writing tools with no system connecting them. This 4-layer framework turns scattered tools into a coherent workflow. - [50 AI Writing Prompts That Actually Sound Like You](https://www.mywritingtwin.com/blog/ai-writing-prompts-that-sound-like-you): 50 ready-to-use AI writing prompts for emails, reports, LinkedIn, and more. Each template includes a Style Profile slot that makes generic AI sound like you. - [AI Editor Comparison 2026: 9 Tools Ranked](https://www.mywritingtwin.com/blog/best-ai-editors-2026): Side-by-side comparison of every major AI editor in 2026. Grammarly, ChatGPT, Claude, Jasper, and more scored on accuracy, voice, price, and integrations. - [ChatGPT Projects Setup 2026: Step-by-Step + Instructions Template](https://www.mywritingtwin.com/blog/chatgpt-projects-setup-guide): Set up a ChatGPT Project in minutes: step-by-step walkthrough, a copy-paste instructions template, and the character limits and settings you'll actually hit in 2026. - [How to Make AI Writing Sound Like You (5 Steps)](https://www.mywritingtwin.com/blog/how-to-humanize-ai-text): Step-by-step guide to making AI-generated text sound like your own writing. Skip the humanizer tools and teach AI your patterns with a Style Profile instead. - [How to Make Google Gemini Write Like You: Setup Guide](https://www.mywritingtwin.com/blog/how-to-make-gemini-write-like-you): Google Gemini sounds generic without style instructions. Set up Gems, Workspace integrations, and Style Profiles to make Gemini write in your voice. - [7 AI Writing Assistant Tricks That Save Hours Every Week](https://www.mywritingtwin.com/blog/7-ways-ai-can-improve-your-writing): From polishing a draft to handling a difficult email, here are 7 practical ways AI can transform your daily writing — and the one thing most people miss. - [How to Build Custom Instructions That Actually Capture Your Voice](https://www.mywritingtwin.com/blog/how-to-build-custom-instructions-that-capture-your-voice): The 7 dimensions your custom instructions need to capture your voice. Most people miss 5. A diagnostic framework for voice-aware AI instructions. - [The Median User Problem: Why AI Was Trained to Sound Like Everyone](https://www.mywritingtwin.com/blog/the-median-user-problem): AI output feels generic because it was optimized to be. The problem isn't your prompting — it's RLHF, a training process that averages out every voice. - [10 Signs Your AI Writing Needs a Style Profile](https://www.mywritingtwin.com/blog/10-signs-ai-writing-needs-style-profile): Keep editing ChatGPT output to 'sound like you'? Your team can tell which emails are AI-generated? Here are 10 signs you need more than custom instructions. - [ChatGPT for Business Leaders: Keep Your Executive Voice](https://www.mywritingtwin.com/blog/ai-writing-for-executives): Executives handle 100+ emails daily. ChatGPT can help — but only if it sounds like you. Here's how to use AI without losing your leadership voice. - [How to Make Claude Sound Human, Not Robotic (2026 Guide)](https://www.mywritingtwin.com/blog/how-to-make-claude-sound-like-you): Stop editing generic AI drafts. The exact prompt and Project setup that makes Claude sound human — and like you — in under 10 minutes. - [Best ChatGPT Custom Instructions for 2026 (Copy-Paste Templates)](https://www.mywritingtwin.com/blog/custom-gpt-instructions-complete-guide): The best ChatGPT custom instructions for 2026 — proven templates and real examples you can copy-paste today, plus the mistakes that make AI sound generic. - [Science of AI Tone: How Machines Capture Your Writing DNA](https://www.mywritingtwin.com/blog/science-behind-voice-profiles): Most AI writing tools are black boxes. Here's the research behind how we make AI actually sound like you, grounded in decades of computational stylometry. - [The Bilingual Professional's Guide to AI Writing](https://www.mywritingtwin.com/blog/bilingual-professionals-guide-ai-writing): AI writing tools fail non-native speakers worse than everyone else. Here's why—and how to make ChatGPT and Claude write in YOUR English, not generic English. - [How AI Style Extraction Works: The Technology Explained](https://www.mywritingtwin.com/blog/how-style-extraction-works): An in-depth look at AI style guide technology. How we quantify something as qualitative as writing style, and why it works across ChatGPT, Claude, and Gemini. - [Why ChatGPT Doesn't Sound Like You (And the Fix That Actually Works)](https://www.mywritingtwin.com/blog/why-ai-writing-doesnt-sound-like-you): You've tried custom instructions, personas, and example text. ChatGPT still sounds generic. Here's the real reason—and how to make ChatGPT write in your voice. ## Multilingual - Available in English, Japanese, French, Spanish, and all languages - Handles language-specific nuances: Japanese keigo levels, French tu/vous formality, cultural communication patterns --- ## Detailed Product Information ### What is a Style Profile? A Style Profile is a document that captures your unique writing patterns — sentence structure, vocabulary preferences, tone variations by audience, formality levels, and rhetorical habits. It consists of two parts: a Writing Style Profile (personalized analysis of your writing patterns and voice) and a Runtime Block (copy-paste instructions for AI tools). Style Profiles are generated from your writing samples using computational stylometry. ### How It Works 1. Submit writing samples (emails, documents, messages) across different contexts 2. Complete a brief questionnaire about your communication patterns 3. Our AI analyzes your samples using computational stylometry techniques 4. Receive your Style Profile: Writing Style Profile + Runtime Block 5. Deploy the Runtime Block in ChatGPT, Claude, Gemini, or any LLM ### Pricing Tiers - **Free ($0)**: Your first use case — one language, one medium, one audience — built from 2,000 words of samples. No card required. - **Starter ($49 one-time)**: Single-language style profile with 3 matrix sections. Includes Writing Style Profile and Runtime Block. 1 generation total (0 regenerations). - **Pro ($99 one-time)**: Multilingual support, unlimited matrix sections, full Style Matrix. 1 free regeneration. Best for professionals who write across languages. - **Executive ($249 one-time)**: Everything in Pro plus audio credits and priority support, plus a $29/yr Unlimited Edits subscription (free for year 1) that unlocks unlimited regenerations. ### Free Writing DNA Snapshot A separate free instant quiz on your writing style (distinct from the free first-use-case profile above). No account required. Paste your writing and get: personality markers, tone indicators, AI readiness score, and a preview of what a full Style Profile reveals. Available at mywritingtwin.com/snapshot. ### FAQ Q: What makes this different from ChatGPT custom instructions? A: Custom instructions are limited to ~1,500 characters and rely on you manually describing your style. A Style Profile is a comprehensive, data-driven analysis of your actual writing patterns — typically 5,000-15,000 words of precise instructions that capture nuances you may not even be aware of. Q: Does it work with all AI tools? A: Yes. The Runtime Block is designed to work with any LLM that accepts system prompts or custom instructions: ChatGPT, Claude, Gemini, Copilot, Perplexity, and API-based tools. Q: How many writing samples do I need? A: Minimum 3 samples across different contexts (e.g., formal email, casual message, report). More samples = more accurate profile. We recommend 5-10 samples totaling 2,000+ words. Q: Is my writing data secure? A: Yes. Writing samples are processed securely and can be deleted at any time. We do not use customer writing samples to train AI models.