Voice guide drafting

Written down once,
writable by anyone else.

Scattered wording samples become a workable voice guide: what to do, what to avoid, a short vocabulary list, and neutral example sentences you can swap. No invented personas or market position, and no unapproved external commitment scripts.

Rules from samplesNeutral examplesCommitments pending

Review the guide

Your result will appear here

We extract the patterns that actually recur, write them as followable rules with contrasting examples, and list commitment wording separately for confirmation.

SAMPLE OUTPUT

Here is exactly what you receive.

This is the complete output for the samples in the demo above: a consistency score, itemised rules, items to confirm before sharing internally, and the voice guide draft. It is a demonstration, not a customer case.

SAMPLE

Draft result (sample)

Consistency score88/100

+50

Trade emotional padding for described actions

The samples are full of endearments and apologies that never say what happens next. The rewritten rules require the next step and its timing.

Pair every rule with contrasting examples

The source offers nothing to model against. Each rule gains a do, a don't, and a replacement using bracketed placeholders.

Pull commitment wording out to a pending list

“As soon as possible” and “we will take this seriously” read as promises. They are excluded from examples and listed as needing confirmation.

Voice guide draft

# Voice guide (draft)

**Rule 1: acknowledge first, then give a time**
- Do: confirm receipt and name when the next step lands or what it depends on
- Don't: write “we will get back to you” with no timeframe
- Example: a reply by [date] / updates as soon as the result is in

**Rule 2: apologise once, then move to the fix**
- Don't: stack exclamation marks and pet names like “dear”
- Example: I have logged this and am doing [action]

**Rule 3: commitment wording stays pending**
- Refunds, remedies, timelines, and recovery windows do not appear in examples
- TODO: confirm which commitment scripts are cleared for external use

**Open question**: whether “dear” as a greeting differs by channel is inconsistent across samples; decide as a team first.

WHAT DRAFTING DOES

Not dictating a tone. Reducing improvising.

A rule has to be followable

“Be friendlier” is not instructions. “When you mention waiting, name the time” tells a writer what to type.

Every rule needs its opposite

Positive instructions alone leave the boundary vague. Pairing each do with a don't and a replacement saves everyone time.

Examples stay swappable

Once a real customer name or a real price sits in an example, nobody dares edit it and the whole block goes stale.

WHY WRITE IT DOWN

Rules nobody wrote are re-argued every time.

Any number of people drift

Five people write one thing five ways. Without a shared reference, you relitigate it at every handoff.

Outsiders can only read the document

Freelancers, agencies, and new colleagues cannot see your judgement — only what you wrote down.

Style quietly becomes a promise

“We will handle it as soon as possible” reads like a commitment. A guide has to separate tone from commitment, and the latter needs an owner.

Note: whatever value consistency has comes from teams actually using and revising the guide; there is no public standard for measuring it and no citable effect percentage. This site works at the writing level only. It performs no user research and offers no compliance or legal advice.

DRAFTING DEMO

The same replies, as rules someone can follow.

Source samples

(excerpts) Hi dear, let us take a look at this and get back to you later. / Found your order number here, we will process it as soon as possible. / So sorry for the trouble, we will take this seriously.

Drafted guide

# Voice guide (draft)

**Rule 1: acknowledge first, then give a time**
- Do: confirm receipt and name when the next step lands or what it depends on
- Don't: write “we will get back to you” with no timeframe
- Example: a reply by [date] / updates as soon as the result is in

**Rule 2: apologise once, then move to the fix**
- Don't: stack exclamation marks and pet names like “dear”
- Example: I have logged this and am doing [action]

**Rule 3: commitment wording stays pending**
- Refunds, remedies, timelines, and recovery windows do not appear in examples
- TODO: confirm which commitment scripts are cleared for external use

**Open question**: whether “dear” as a greeting differs by channel is inconsistent across samples; decide as a team first.

Demo sample: politeness becomes a concrete action, commitments are listed separately rather than drafted, and examples carry swappable placeholders. Paste your samples to get your version (sign-in required; one credit per run).

WHY YOU CAN TRUST IT

We put “no invented personas” into our product principles.

Only patterns the samples show

Rules come from wording that recurs, not from an imagined target reader. Whatever the samples do not support never becomes a rule.

No personas or market position

Age breakdowns, survey numbers, user sentiment, and industry standing are absent, along with any hint of how readers should feel about the brand.

Commitment wording listed separately

Refunds, remedies, timelines, and availability promises are not drafted as final copy; they are marked pending the person who carries the risk.

Content is not stored

Submitted text is used for this single AI request and is not intentionally persisted. See the Privacy Policy.

FAQ

Ask these before you pay.

Are a few samples enough?

Enough to start. Fewer samples means fewer and more conservative rules, and contradictions appear as open questions rather than as a choice we make for you.

Will you draft refund or remedy wording?

Not as finished copy. External commitments are listed separately with a note on whose clearance they need before use.

Can I use the example sentences directly?

Yes, once you replace the bracketed placeholders with your own details. The examples are deliberately neutral, with no real customers or concrete figures.

What does one draft cost?

One credit per run, usually done in seconds, returning the guide, the rule reasoning, and items to confirm.

Do credits expire?

No. Credits never expire — whatever you do not use carries over to the next cycle instead of resetting.

Is there batch processing or an API?

Not yet. Each run processes one document and consumes one credit; there is no bulk upload or API today. Email us with your use case and we will assess it.

Is my content stored?

Not intentionally. Text is used for this single AI request only. See the Privacy Policy.

Which material fits?

Support replies, sales conversations, emails, chat responses, product copy excerpts — several real passages your team has actually written, in Chinese or English.

SIMPLE PRICING

Prove the value before you upgrade.

Starter

$9/ month

For an occasional publishing cadence, with a focused monthly credit allocation.

50 optimization credits per monthly renewal
Complete GEO analysis
Chinese and English output
Markdown export

Pro

Recommended$29/ month

For frequent publishers who iterate on content continuously.

250 optimization credits per monthly renewal
Complete GEO analysis
Chinese and English output
Markdown export

Advanced

$79/ month

Our largest monthly credit allocation, for the heaviest continuous usage.

1,000 optimization credits per monthly renewal
Complete GEO analysis
Chinese and English output
Markdown export

Credits never expire: unused credits carry over instead of resetting. Credits apply to this site only and are not shared with other sites.

Prices shown are USD baselines; final currency, taxes, and discounts are determined by Paddle for the checkout location.