The eleven questions
Most tools in this category hide their questions behind a submit button. Of the forty-nine surveyed, the median number asked was between one and four, and the most common number was one. That is worth knowing before you trust any of them with your voice.
So here is the whole set, word for word, with the reason each question exists and, more usefully, the four standard framings that were considered and thrown out. The rejected half is the part a competitor cannot copy without revealing what their own four dropdowns are doing.
This page sits under brand voice guidelines, and you can answer the questions themselves in about five minutes if you would rather do than read.
What has to be asked before a rule can be written?
Three things, and only three. Who is speaking, who is being spoken to, and what the mechanical settings are. Everything else in a typical brand voice exercise is either downstream of those or is not a writing rule at all.
That is why the set is eleven rather than forty. A question earns its place by changing something in the output. If two different answers produce the same file, the question is decoration and it costs the person filling it in more than it gives them.
The eleven questions, verbatim, and why each one is asked
This table is generated from the questionnaire itself rather than copied, so it cannot drift from what the tool actually asks.
| The question | Why it is asked |
|---|---|
| What are we naming this voice after? | Because a model follows a named subject better than it follows “the brand”. This name is the first line of every file we make. |
| In one sentence, what does your brand do? | Because an assistant needs to know what you do before it can sound like you. One plain sentence is enough. |
| Who reads what your brand writes, most of the time? | Because the reader decides how much you have to explain. The same sentence is right for one group and wrong for another. |
| Which of these sounds more like your brand? | Because formality is the dimension people are least able to name and most able to recognise. Two paragraphs settle it faster than a scale. |
| And these two? | Because humour is the riskiest thing a brand does. A brand that decides against it is making a real decision, and we write that down. |
| Two ways of writing about your own industry. Which is closer? | Because how you treat the subject and how you treat the reader are different dials, and assistants collapse them into one. |
| Last pair. Same results, written two ways. | Because enthusiasm is where assistants overshoot first. Naming the level gives us something to hold them to. |
| What should you never sound like? | Because “warm” means something different to everyone, and “never cold” doesn't. Saying what you're not gives us a line we can check writing against. |
| How does your brand refer to itself in writing? | Because the right answer is different for almost every brand, and the wrong one shows up in your first sentence. We've seen two guides by the same writer give opposite rules on this. Both were right. |
| “We're” or “we are”? | Because it is the single fastest way to move how formal you sound, and an assistant will pick for you if you don't. |
| Which English does your brand write in? | Because spelling is the most visible tell there is. A British brand whose assistant writes “optimize” has been caught. |
Why do four of them show two paragraphs instead of a scale?
The four tone questions are a forced choice between two written paragraphs saying the same thing two ways. You pick the one you would rather send.
That format was chosen against the evidence on the alternatives, and it does two jobs at once. It settles the dimension, and the paragraph you picked ships in your file as a worked example. Examples do more work than descriptions: a few of them, chosen for spread, move how accurately a model reproduces a voice by far more than an adjective does.
The questions we cut, and what was wrong with them
These are not oversights. Each is standard practice somewhere in the category, and each was rejected for a stated reason.
- A single global tone setting. Every one of fourteen published brand guides surveyed encodes tone as a function of the surface rather than as a constant. One dial for a whole brand is the most common failure of free voice generators, and it is beaten by asking about surfaces instead.
- Adjective-picking, in all its forms. Practitioners are blunt that clients cannot answer it, and the output is unusable anyway, because warm means something different to everybody including the model.
- Sliders and the tone spectrum they come from. This is the single most requested visual in the category. Sliders raise item non-response, raise break-off sharply, and fail worst among exactly the respondents this tool is for.
- Rating scales, star ratings and agreement items. Forced choice produces significantly more reliable results, which is why the four tone questions are pairs rather than scales.
- Any question whose only purpose is to add a rule beyond the fifteenth. The cap is a design constraint rather than a limitation, and a question that can only push you past it is a question that makes your file worse.
Why are there no brand archetypes here?
The twelve archetypes and the four-dimension tone model are the two frameworks this category is built on, and neither produces writing rules. They are diagnostics of perceived personality: useful for deciding what a brand should feel like, silent on whether to use contractions.
The four-dimension model in particular is worth knowing the provenance of. It rests on one study of fifty respondents, published in 2016 and never replicated, and it is the entire evidential basis for several tools currently ranking for these terms. It is not wrong. It is just not a source of instructions a model can follow.
Why are you not asked to paste your best copy?
You can, and it is offered as an accelerator. It is never required, for two reasons.
The first is that samples tell you what a brand has done rather than what it has decided, and the two differ most in exactly the places a rule is needed. The second is privacy: nothing here is stored or transmitted, and a method that depends on uploading your copy somewhere would be a different product with a different promise. The privacy page sets out what that means in practice.
What the answers turn into
One canonical document, from which every file in the download is rendered. The mechanical answers become binding rules, the forced-choice paragraphs become worked examples, and the never-sound-like answer becomes the prohibition list that a style checker can enforce.
The manifest lists every file and where it goes, and the verification page is the ninety-second check on whether any of it made a difference.
Where these come from
Every claim above is quoted from one of these, and each was read on the date beside it. If one of them has changed since, the page is wrong and we would like to know.
- Nielsen Norman Group: the four dimensions of tone of voice checked 2026-08-16
- Mailchimp content style guide, tone by surface checked 2026-08-16
- GOV.UK style guide, tone by context checked 2026-08-16
The questions above are the whole set, and there is nothing behind them you have not seen: answer the eleven and keep the folder.