HomeAI Detector › Score Your Newsletter for AI

Score your newsletter for AI — voice consistency before you hit send.

Paste the draft, get a 0-100 score in 30 seconds, and run a voice-consistency check against your last three issues so you can see if Issue 47 still reads like Issue 1. The classifier flags where ChatGPT defaults flattened your openings, your sign-offs, and the small specifics that made paid subscribers say yes in the first place. Built for weekly thoughts, curated link roundups, deep-dive essays, news digests, and paid-only premium issues across Substack, Beehiiv, Ghost, and ConvertKit. Free, no signup, no card. The point is the 30 seconds before send, not the rewrite after.

Score my newsletter free See pricing
0-100 score in 30 seconds Voice-consistency check Sentence-level highlights Substack + Beehiiv ready
Why the inbox is different

A newsletter score matters more than a blog post score.

A blog post can be skimmed by anyone. A newsletter is opened by people who already said yes to hearing from you. They handed over inbox space, which is the most protected piece of real estate they own. The 30 seconds before send are the cheapest insurance against the slow drift that breaks that contract.

Subscribers paid attention for your voice

Readers have other places to find information. What they cannot get anywhere else is the specific way you notice things. ChatGPT defaults flatten that exact thing. A subscriber who opens three generic-sounding sends in a row will not unsubscribe with a complaint email. They simply stop opening. By the time you see the drop in the open-rate chart, six weeks of damage are already locked in.

Inbox providers watch engagement too

Gmail, Outlook, and Apple Mail use opens, replies, scrolls, and deletes-without-open as inputs into where future sends land. Newsletters deleted unopened drift from the primary inbox into promotions, then into spam. AI prose correlates with both fewer opens and more unsubscribes, so the score is an indirect predictor of deliverability across the next six to twelve sends, not just the one in your hand.

Paid renewal is the slowest, most consequential signal

Open rate bends slowly. Click rate moves first because readers stop clicking links inside an issue that did not feel worth finishing. Paid renewal is the lagging signal. By the time it shows up on the dashboard, four to eight issues of voice drift have already compounded. Voice consistency is a forward-looking metric the dashboard does not track for you, which is why the pre-send check has to.

There is no undo button

A blog post can be edited after publishing. A send cannot. Once the newsletter ships, every subscriber sees whatever the score reflected at the moment you clicked. That is why the 30 seconds before send are worth more than any other moment in your writing process.

The send-day workflow

Four steps from finished draft to scheduled send, in fifteen minutes.

The point of the score is not to chase a number. It is to catch the moments where the prose stopped sounding like you. Four steps, fifteen minutes, no rewrite tool required for most issues.

Step 1: Paste the issue, read the 0-100 score

Drop the full body of the newsletter into TextSight before you do anything else. The score returns in 30 seconds with a colour-coded sentence map: red for high-risk lines, yellow for borderline, green for safe. Aim above 70 for general content and above 80 for paid-only issues. Below 60 is where unsubscribes start showing up on the next two or three sends.

Step 2: Run the voice-consistency check vs prior issues

Paste your last three issues from the archive into the consistency panel. The classifier compares opening rhythm, sentence length distribution, sign-off pattern, and vocabulary density between the new draft and the historical baseline. If the new issue drifts more than 20 points from your normal range, you get a voice-drift warning even if the AI score itself looks fine.

Step 3: Review the red sentences for generic phrases

The colour map points at the 20 percent of the draft that is causing 80 percent of the problem. Scroll the highlighted view and read each red sentence aloud as if you were saying it to a subscriber in a coffee shop. If it sounds stiff or could open any newsletter on your topic, replace it. Most red sentences cluster in three places: opener, bridges between sections, and the sign-off.

Step 4: Revise the generics, re-scan once, ship

Edit the red sentences in your own voice. One specific concrete noun per red sentence (a name, a place, a number that is not round) is usually enough to flip the colour. Re-scan once to confirm the score moved into the safe band, then schedule the send. Scanning every revision turns the score into a target you optimise for, which makes the prose flatter, not better.

Score bands

Five bands tuned for newsletter context.

The bands below are calibrated against paid-newsletter outcomes. The thresholds are tighter than for blog content because subscriber inboxes are a higher-trust surface than a public web page.

0-20: Original — ship as is

Reads like you wrote it between coffee sips. Sentence rhythm varies, asides appear where a human voice would put them, and the small word choices feel personal. This is the band where loyal subscribers reply to the email instead of just opening it. Open rate, click rate, and paid renewal all hold at their normal level.

21-40: Mostly Human — optional polish

A few tells, usually clustered around section transitions or the closing call to action, but subscriber-safe overall. Open rates and reply rates should sit at their normal level. Two minutes of editing the red sentences moves this into the top band if the send is going on a high-traffic day or a paid renewal cycle.

41-60: Mixed — edit before sending

Open rate on the next send drops slightly, usually two or three points. Attentive subscribers notice the prose feels off without being able to name why. The fastest fix is to rewrite the first paragraph in your voice and strip the worst AI-tell words from the rest. Do not ship at this score for a paid list.

61-80: Likely AI — pull the schedule

Unsubscribes spike on this send. Expect a measurable bump in opt-outs within 24 hours and a noticeable drop in opens on the send after this one. Most loyal readers recognise the prose is not yours. Do not ship this send under your byline. Restructure the draft or pull the schedule by a day and rewrite.

81-100: AI Generated — throw out the draft

Mass unsubscribe plus spam reports. This is an unedited ChatGPT or Claude draft. Subscribers report the email as spam in numbers large enough to hurt sender reputation across your whole domain, not just this list. Throw out the draft, start from a real observation, and rewrite from scratch.

What this scores

Tuned for the five newsletter formats operators actually ship.

The detector was calibrated against newsletter content across the five formats below. ChatGPT defaults toward slightly different patterns in each one, and the score weights adjust so the band you land in is calibrated to the register the format actually needs.

Weekly thoughts and short personal essays

The 400 to 1,000 word personal-essay format that anchors most independent newsletters. Voice is almost the entire value here, so this is where the score matters most. Target above 75. The classifier weights opening rhythm and sentence length variance heavily because that is what subscribers internalise across Issues 1 through 3.

Curated link roundups

The "five things I read this week" format. The risk is parallel structure across items reading uniform. The score flags roundups where every item has the same length, the same connective tissue, and the same neutral framing. Target above 70. Roundups have lower voice density than personal essays, so the band can be slightly looser.

Deep-dive essays and long-form analysis

The 1,500 to 4,000 word issue paid subscribers usually expect at least once a month. ChatGPT structures these cleanly with template H2s and bullet-heavy bodies, and the cumulative effect is what reads AI. Score the issue section by section if it is over 5,000 characters. You do not need to rewrite the whole essay, just the sections with the highest density of red sentences. Target above 80 for paid deep-dives.

News digests and weekly recaps

News-style summaries of the week's important stories in your beat. Summaries are inherently structured, so it is easy for the prose to read template. The score flags digests where every story is framed the same way and where editorial reaction is missing. Add a one-sentence opinion per item. That is the move that turns a digest into something a subscriber would pay for.

Paid-only premium content

Subscriber-only deep dives, frameworks, interviews, and analysis. This is the format where the score matters most because the value proposition is your specific judgement. Target above 80. Add an experience anchor every 400 to 600 words: a specific number, a client name with permission, a concrete failure, an opinion the model would not commit to. The classifier flags where these anchors are missing.

Plans & pricing

Same scorer at every tier.

Free covers a couple of issues a week. Pro is $19.99 monthly or $14.99 effective on yearly. Business adds API access for automated pre-send checks across multi-title teams. Full details on the pricing page.

Free
$0/forever

 

Try the newsletter scorer. No card, no email.
  • 0-100 score in 30 seconds
  • Sentence-level highlights
  • Voice-consistency check
  • 1,500-word AI rewriter quota
Start free
Starter
$7.49/month

Billed $89.88/year — Save $30

For operators shipping one issue a week.
  • 20,000 AI rewriter words/mo
  • Chrome extension
  • Substack + Beehiiv ready
  • Email support
Get Starter
Business
$29.99/month

Billed $359.88/year — Save $120

For newsletter teams running multiple titles.
  • 150,000 AI rewriter words/mo
  • REST API + pre-send hook
  • 5 team seats
  • White-label PDFs
Get Business

Yearly billing saves 25%. View full pricing →

What to revise

The generic phrases subscribers learn to ignore.

Most red sentences in newsletter drafts share a small set of patterns. None is wrong in isolation. The problem is the cumulative effect when subscribers see the same patterns across two or three issues. The scorer flags them so the five minutes before send go to the right lines.

Openings that could open any newsletter on your topic

"I have been thinking about," "Here is what stood out this week," "Let me share a quick observation." None of these is bad writing in isolation, but if every issue opens with one of them, regular readers notice by Issue 3. Replace the opening with something that describes a specific moment from your actual week: a place, a name, a number that is not round.

Sign-offs that thank the reader for reading

"Thanks for reading," "Until next week," "Talk soon." The closing meta-paragraph is where ChatGPT is least varied. The scorer flags it because the sign-off is the highest-recall part of a newsletter, the line subscribers see right before they close the email. Either rotate across three or four genuine closing patterns or drop the meta-close entirely and end on the last substantive line.

Hedged middle paragraphs

"It can be argued that," "in many cases," "it is worth noting that." This is the most damaging tell for paid content. Paid subscribers paid for a specific point of view, and hedged prose reads as a researcher's summary rather than as your judgement. The scorer sharpens these lines and flags where you should commit to a position instead of presenting two balanced perspectives.

Eight words to find-and-replace in one pass

Delve, leverage, robust, navigate, underscore, showcase, myriad, tapestry. These cluster in AI-drafted newsletter prose because they were optimisation targets in marketing training data. If you cannot replace one without losing the meaning, the sentence needs a real rewrite, not a single-word swap.

Evenly weighted list items

In a roundup or weekly-thoughts issue, ChatGPT defaults to list items of roughly the same length, the same sentence structure, and the same emotional register. Real human roundups have one item that runs three times as long because you had more to say, one item that is two sentences because there was not more to say, and one item that breaks the parallel structure entirely. The scorer flags the symmetry.

The consistency check

Does Issue 47 still read like Issue 1?

The AI score on its own does not catch slow drift. A newsletter can score 75 and still sound like nobody in particular. The voice-consistency check compares the new draft against your last three issues so you catch the gap the score misses.

How the consistency baseline is built

Paste your last three issues from the archive into the consistency panel alongside the new draft. The classifier extracts four features from the historical baseline: opening rhythm, sentence length distribution, sign-off pattern, and vocabulary density. The baseline is a small statistical fingerprint of what "your voice" has looked like across recent sends.

The drift warning, and what 20 points means

If the new draft falls more than 20 points outside the baseline range on any one feature, the panel returns a voice-drift warning. A 20-point drift is the threshold where regular readers start internalising the new issue as a different writer. Below 20 they cannot name the change. Above 20 they can. The warning is feature-specific so you know whether to rewrite the opener, the cadence, the sign-off, or the vocabulary.

The friend test the numbers cannot do for you

After the score and the consistency check, run one last sanity check. Imagine a close friend who reads your newsletter every week and knows the way you talk. Imagine the subject line and first paragraph of this send arriving in their inbox without your name on it. Would they recognise it as yours? If no, the draft needs one more pass, no matter what number the scanner returned.

Why one specific noun usually flips a red sentence

The classifier reads specificity as a strong human signal because AI defaults toward category-level abstractions. Replacing a vague claim with one concrete noun (a name, a place, a number that is not round, an exact moment) is usually enough to move a red sentence into yellow or green. One specific noun per red sentence beats ten generic-word swaps.

FAQ

Newsletter scorer frequently asked.

What newsletter score should I aim for before I hit send?
For a paid newsletter or any list where subscribers chose you for your voice, target 80 or higher. For a transactional weekly digest where voice matters less, 70 is acceptable. Below 60 is where open rates start drifting down and unsubscribes begin to spike over the next two or three sends. The bar is higher than for blog posts because subscribers paid attention with their inbox, which is the most protected piece of real estate they own.
How does the voice-consistency check work against my prior issues?
Paste the new issue, then paste the last three issues from your archive. TextSight compares opening rhythm, sentence length distribution, sign-off pattern, and vocabulary density between the new draft and the historical baseline. If the new issue drifts more than 20 points from your normal range, you get a voice-drift warning alongside the AI score. This catches the case where the AI score looks fine but the issue still does not read like you.
Can I score my whole newsletter on the free tier?
Most newsletters fit. Free gives a 1,500-word AI rewriter quota and detector scans for full-length issues. A typical newsletter runs 3,000 to 8,000 characters, which is well inside the per-scan limit. You can scan the intro, body, and PS together or split into sections to focus the colour map on the part you are unsure about. One re-scan after edits is built into the free workflow.
Will Substack, Beehiiv, Ghost, and ConvertKit flag my newsletter as AI?
None of these platforms applies a visible AI tag to outgoing sends today. The risk is on the recipient side. Inbox providers quietly weight engagement signals, and a newsletter that triggers deletes-without-open or spam complaints sees its sender reputation drop. AI prose correlates with both behaviours across four to six sends, so the score is an indirect predictor of deliverability and paid-renewal rate over time.
Should I score the subject line and preview text too?
Yes, but read them by eye in addition to the score. Subject lines are usually under 60 characters, and any AI classifier becomes unreliable below 200 characters. The score on one short line can swing 30 points on a single word. Run the subject line and preview text together as a bundle so the classifier has context, then trust your own ear for whether the line sounds like a sentence you would say out loud.
How is this different from the newsletter AI rewriter page?
The scorer tells you whether the draft is safe to send. The AI rewriter rewrites lines that are not. Most newsletters do not need authenticity — they need a 30-second sanity check. If your score comes back in the 70s or higher, ship it. If it drops below 60, edit the red sentences yourself when you can, which preserves your voice better than any rewrite tool. Use the AI rewriter when a Balanced-mode pass is the faster path on a deadline.
What if I draft with ChatGPT and only edit lightly?
Light editing rarely moves the score above 65 because the underlying sentence rhythm and vocabulary survive a polish pass. To pull a ChatGPT draft into the safe band, rewrite at least the opening paragraph, the section bridges, and the sign-off in your own words. Use the AI draft as a structural outline, not as the prose you ship. Two minutes of real rewriting beats ten minutes of finding and replacing single words.
How often should I rescan a newsletter draft?
Twice per send. Once after the first draft to see where the problems are, then once after editing to confirm the fixes landed. Scanning between every paragraph rewrite turns the score into a target you optimise for, which usually leads to flatter prose rather than better prose. The score is most useful as a yes-or-no signal at two checkpoints, not as a real-time gauge you watch while writing.
Related

More for the newsletter workflow.

Check your newsletter draft. Send in your own voice.

Free to try, no card. 0-100 score in 30 seconds, voice-consistency check vs prior issues, sentence-level highlights.

Score my newsletter free See pricing
Voice-consistency tool · Open-rate aware · Substack, Beehiiv, Ghost, ConvertKit