# Key
—
# Contexts crossed
—
# Questions written
—
# Jobs found
—
A free allowance per visitor, no account needed.
Why a keyword is not a question
Search boxes taught two generations of people to compress. You do not type what you want; you type the two words most likely to be indexed against it, and you do the rest of the work yourself by scanning ten blue links. Every keyword tool ever built measures the output of that compression — which is why a keyword list tells you what people typed and never what they needed.
An assistant removes the reason to compress. There is no box, no ten links and no penalty for a full sentence, so people say the whole thing: the urgency, the device in their hand, the document on the table, and the specific way it is going wrong. The question that reaches a model is longer, stranger and far more specific than anything in a keyword report — and it usually does not contain the keyword at all.
That is the gap this tool works in. It does not find you more keywords. It takes one keyword and reconstructs the situations that get compressed into it, then writes what somebody standing in each of them would say.
The four axes
Each question is one crossing, and it carries the labels it came from.
01 · Urgency
How much time there is. The same need phrased at leisure and phrased in a panic retrieves different pages, and the panicked phrasing is the one nobody writes for.
02 · Who is asking, and on what
A phone with nothing installed asks a different question from a desk with everything installed. So does somebody with a colleague standing over them.
03 · The thing in front of them
Not the category — the actual document, account, report or person. “A document” is a keyword. “The lease the agent is waiting for” is a question.
04 · What is going wrong
The mistake already made, the thing that cannot be found, the thing they are afraid of getting wrong. This is the axis that produces the questions worth a page.
How to read the result
The questions are grouped by the job somebody is doing, not by how similar the wording is. That grouping is the useful part: a job is something you can write one page for, and a wording cluster is something you can only write one paragraph for.
A job, not a cluster
Each group is a situation with a beginning and an end — somebody with a lease to sign before an office closes. If two groups could share one answer, they are one job and one page.
The labels under a question
They name the crossing it came from, so you can throw away a whole branch at once: if nobody in your market is ever on a phone, drop every question carrying that label instead of reading them one at a time.
The questions without your keyword
Those are the valuable ones, and they are why this is not a keyword tool. A question still containing the head term is one your existing page probably answers. A question that describes the problem instead is the one your competitor has not written yet.
The count, stated
The strip says how many questions came back and how many were asked for. A run that returns nine of twelve says nine — a tool that prints its target and shows its result reads as complete when it is not.
What this tool can and cannot tell you
This page answers one question for one keyword, honestly, which means naming what it cannot see as clearly as what it can.
What it can tell you
- The shapes a keyword takes when it is spoken instead of typed, as full sentences you can read out loud and judge.
- Which life context produced each phrasing, named, so you can tell a real job from a reworded keyword.
- Which situations around your keyword you have never written a page for — usually the urgent ones and the frightened ones.
- A starting set of headings in the words a reader would use rather than the words a keyword tool would.
What it cannot tell you
- How many people ask any of these. There is no volume here and none is implied: every question is a hypothesis about phrasing, not a measurement of demand.
- That anybody has ever asked one of them. They are written from a framework, not harvested from a query log, and this version cross-checks them against nothing.
- Whether an assistant answers with your page today. That is a measurement over time on prompts you choose, not a property of one keyword.
- Which question is worth your week. It names the job; the judgement needs a market you know and we do not.
Using the questions
The output is not a keyword list to sprinkle. Each group is a candidate page, and each question is a candidate heading in the words a reader would actually use.
- 1
Take one group, not the whole run
One job, one page. A page trying to serve four jobs answers the first sentence of each and is retrieved for none, because a passage has to stand alone to be quoted.
- 2
Use the question as the heading
Verbatim, including the awkwardness. A heading matching the question somebody asked is the largest retrieval improvement available on most pages, and smoothing it into marketing language undoes exactly that.
- 3
Answer in the first sentence
Yes, no, usually, it depends and on what. A paragraph that clears its throat before answering gives a retrieval system nothing to lift, however good the third sentence is.
- 4
Check the page can be read
Then run it through Vectorscope. A question answered in a passage that falls outside the retrieval cap is a question you have answered for nobody.
Frequently asked questions
What is Voicescope?
A free tool that takes one search keyword and shows the questions people speak to an AI assistant instead of typing it. It crosses the keyword with four real-life contexts — urgency, device, the document in front of them, and what is going wrong — and writes the sentences that result, grouped by the job somebody is doing. No account, no payment.
How is this different from a keyword tool?
A keyword tool reports what people typed, which is already compressed: the two words most likely to be indexed, with the situation stripped out. This works the other way — it starts from the keyword and reconstructs the situations compressed into it. The output is sentences rather than phrases, most of which do not contain the keyword, and there are no volume figures because nothing here has been counted.
Are these real searches that people have made?
No, and the tool never says otherwise. They are written from a framework, not harvested from a query log, so each one is a hypothesis about how a need gets phrased out loud. That is genuinely useful for deciding what to write and genuinely useless as a demand estimate, and confusing the two is the mistake this answer exists to prevent.
Does it work for languages other than English?
Yes. The questions are generated in the language you ask for, written in that language rather than translated out of English — a phrasing translated from English is an English phrasing with foreign words in it, which is the opposite of what this measures.
What is JTBD, and why use it here?
Jobs-to-be-Done is the idea that people do not want a product, they want a job finished. It fits here because a spoken question is a job description: the urgency, the constraint and the obstacle are all in the sentence. Grouping by job rather than by wording is what makes the output a set of pages to write instead of a list of phrases to sprinkle.
Is it free, and what is the catch?
Free, with an allowance per visitor so one person cannot spend the day's budget. No account, no trial, no card. The catch, such as it is, is that the tool does one thing: it will not measure whether an assistant names your brand, because that takes repeated checks on prompts you choose over weeks, which is the paid product.
Can I use the output on my own site?
Yes, without attribution. Write the pages, use the questions as headings, put them in an FAQ — they are yours. Two cautions: read each one out loud before publishing, because a question that sounds wrong to you will sound wrong to a reader, and do not paste all twelve into one page, which is how a page ends up serving four jobs and being retrieved for none.
Words used on this page
Four terms, defined once, because a page that uses them without defining them is a page an assistant cannot explain to anybody.
Conversational query
A question phrased as speech, carrying the context a keyword drops.
Conversational query →