Author guideWriting voiceCraft, not filters

Preserve your writing voice with AI

AI sounds generic when nobody told it whose voice to write in. Define the eight choices that make a voice yours before you draft — then hold every draft to them.

Editorially reviewed by David Weaver, BookWriter founder and bestselling author since 2008 · Updated July 17, 2026

Direct answer

How do I make AI writing sound like me?

Preserving voice starts before you draft, not after. Define eight things — point of view, tense, narrative distance, rhythm, diction, dialogue behavior, image system, and hard avoids — then judge every draft against those choices and revise what breaks them. That is how AI writing ends up sounding like you: you set the standard, and hold the prose to it.

Free builder

Author Voice Contract

Decide the eight choices that make a voice yours before you draft. Then every draft has a standard to be judged against — not a filter to be run through afterward.

0/8 defined
Your voice contract
AUTHOR VOICE CONTRACT
Judge every draft against these. Where a draft breaks one, revise the draft — not the contract.

Point of view: —
Tense: —
Narrative distance: —
Sentence rhythm: —
Diction: —
Dialogue: —
Image system: —
Hard avoids: —

This defines voice up front so you can evaluate a draft against your own choices. It is not an AI-detection workaround — it is the opposite: a standard you set, then hold the writing to.

Specify it, then enforce it

Voice is a set of decisions — here is how to name and hold them

Writers worry that using AI will sand their voice down to a smooth, anonymous gloss. The worry is legitimate — but the cause is almost always the same, and it is fixable. Generic prose is what a model produces when nobody told it whose voice to write in. Voice is not something you rescue after the fact with a "humanizer"; it is something you specify before the first sentence and enforce on every draft.

Voice is a set of decisions you can name

It is tempting to treat voice as a mystical quality, but on the page it decomposes into concrete, repeatable choices. Who narrates, and how close are we to them? Past or present? Long, rolling sentences or short, clipped ones? Plain diction or ornate? Do characters speak in subtext or say what they mean? What images recur? And crucially — what do you refuse to do? Every one of those is a decision you can write down, hand to a collaborator human or otherwise, and check a draft against.

That is why the fix for "AI sounds generic" is not a better prompt like "write in my voice" — the model has no idea what that means. It is a specification. The eight-part contract above is that specification: it turns the intangible into eight instructions concrete enough to enforce.

A worked revision: one paragraph, held to the contract

Suppose the contract says: past tense, close third on Mara, short sentences, plain concrete diction, a recurring salt-and-tide image system, and a hard avoid on rhetorical questions and the word "suddenly." Here is a generic draft:

DRAFT: "Suddenly, Mara felt a wave of overwhelming emotion wash over her as she gazed out at the vast, glittering expanse of the ocean. What did the future hold for her now? Everything had changed, and she knew that nothing would ever be the same again."

Now the same beat, revised against the contract:

REVISED: "The tide was going out. Mara watched the water pull back from the rocks, leaving them slick and black. Her hand found the salt-crust on the rail. Whatever came next, it would not be this."

Every change traces to a rule, which is the point — nothing here is taste for its own sake:

  • "Suddenly" is gone — it was on the hard-avoids list.
  • The rhetorical question ("What did the future hold?") is cut for the same reason.
  • "Overwhelming emotion" and "vast, glittering expanse" go — the contract asks for plain, concrete diction, so we show the tide, not the feeling.
  • Salt and tide do the emotional work — that is the declared image system earning its place.
  • Sentences are short and we stay inside Mara’s senses — close third, the declared distance and rhythm.

Notice what this is not: it is not a pass to "humanize" or disguise anything. It is craft — a draft measured against choices the author made, and revised where it fell short.

The honest take on "humanizing" AI writing

Search interest in "humanizing AI text" is usually really a search for this: writing that sounds like a person because a person made real choices in it. The reliable way to get there is the contract-and-revision loop above. It produces prose that is genuinely yours, not prose engineered to fool a detector — and it holds up to the only audience that matters, which is a reader.

This page deliberately stops there. Defining and enforcing your voice is craft worth teaching. Tools built to evade AI detection are a different thing with different aims, and they are not what this is about. Do the craft, and the "does this sound human" question mostly answers itself.

Keep the contract where the book applies it

A voice contract you write once and lose is a voice contract you stop enforcing. The reason voice drifts across a long AI-assisted book is that the standard lived in a chat that scrolled away, so nothing was holding chapter twenty to the choices you made in chapter one. The contract has to persist, and it has to be applied.

In BookWriter, an approved voice contract lives with the project as a rule the drafting can be held to, chapter after chapter. You keep writing in whatever conversation you like; the standard travels with the book, so the last page sounds like the same author who wrote the first.

Definition

A voice contractan explicit statement of the repeatable choices that make writing yours — point of view, tense, narrative distance, rhythm, diction, dialogue behavior, image system, and hard avoids — set before drafting so each draft can be judged against it.

Product previewAvailability

The Voice Contract method works with any workflow today. Keeping the contract as an approved rule a connected assistant applies per chapter is part of the Product-preview connected workflow — a private developer-mode connection, not a public app-directory listing.

Connect BookWriter to ChatGPT through a private developer-mode app: in ChatGPT on the web, open Settings → Apps → Advanced Settings and enable Developer mode. Then open Apps, choose Create, paste the BookWriter MCP server URL, authorize with your BookWriter account, and scan the tools. Full connected write actions currently require an eligible ChatGPT Business, Enterprise, or Edu workspace.

See the current setup guide

A standard the book keeps

Save the contract with the project

A voice contract only preserves your voice if it is applied to every chapter. In a BookWriter blueprint it becomes a rule that travels with the book. Your included Connect book is free, and drafting never spends the allowance.

The included offer

1 persistent connected book

Up to 50,000 accepted words, with no BookWriter credit card. Drafting and previewing never spend the allowance — only an explicit save counts an accepted chapter toward it.

Refer 3, keep 100,000

When 3 different referred authors verify new accounts and start their own included Connect books, your original free book permanently expands to 100,000 accepted words.

Keep your voice from chapter one to the last page

Start your included Connect book and save your voice contract with the project, so every chapter is held to the same choices.

Your included book is free, with no BookWriter credit card. Drafting and previewing never save prose.

Frequently asked questions

Sources

Verified on July 17, 2026

  • Author Voice ContractBookWriterThe public contract for approving and persisting voice rules with a book project.
  • Steering Connect Agent GuideBookWriterThe connected workflow’s public boundary: approved state, bounded retrieval, and explicit saves.

Platform specifications, policies, and product behavior change. Each source is dated above; verify against the primary source before relying on it for a print run or submission.

Keep building in the writing system

Read the documentation →