Brand Voice Checker

Check a draft against your own voice rules: the words you never use, the phrases you do, and one reading-level ceiling. Every block comes back pass or revise, with each finding quoted in the sentence it appears in.

All free tools — Brand Voice Guide template

A conformance check is the mechanical half of review. It matches words and their ordinary forms, so it misses paraphrases, and it lists mentions inside quotation marks without counting them. It runs the same engine as the brand-voice-governance agent skill. It is a floor for review, not a replacement for a person reading.

Run this in your agent

The free AAJ agent skill Brand Voice Governance does this job inside a coding agent, on your own data. Install it with npx skills add sarojkjha/aaj-marketing-skills --skill brand-voice-governance.

Using Claude or ChatGPT instead? Add the AAJ engines as a custom connector, with no install: https://aaj-engines-mcp.sarojkjha10.workers.dev/mcp

Frequently asked questions

Can software check content against brand voice rules?

Yes, for the mechanical part — banned words and reading level. It misses paraphrases, so it is a floor for review rather than the review.

Why does a banned list on its own not work?

Give a model a banned list and nothing else and it routes around the ban into a different flavour of generic. The positive list is what turns avoidance into a voice.

Which reading grade should I set?

One number, chosen by you. The grade here is Flesch–Kincaid, computed in your browser from sentence and syllable counts.

Is anything stored or shared?

No. The rules and the draft never leave your browser. Nothing is saved or sent, and refreshing clears it.

More in Brand & Voice

Part of the Brand & Voice hub - see all 11 resources on this topic.

Also useful in Content, Copy & SEO, Marketing Ops, AI & Team.