Scan every blog post, email, social caption, paid ad, and landing page before publish. Brand voice consistency across in-house writers and outside agencies, sentence-level highlights to flag the AI passages, audit log on Business, REST API for CMS integration. Built for in-house marketing, content, and brand teams shipping fifty or more assets a month. Free to try. No card.
SaaS marketing functions, DTC content teams, mid-market B2B content shops, and the brand-side of any in-house marketing org. Five to fifteen writers, two or three AI tools in the stack, a content calendar that ships weekly, and at least one outside agency in the rotation.
Marketing teams answer to executives who read the published output. The CMO scans nurture emails on Monday morning. The CEO opens the company blog before a board meeting. Sales leadership pulls landing pages during weekly pipeline reviews. Every surface gets read by someone with authority over the marketing function and no time to review drafts. The published piece is the only signal they have, and a templated AI tone reads as a brand problem rather than a writer problem.
Four to eight named writers on staff, often a senior editor or content lead, sometimes a brand strategist. Every writer drafts with at least one AI tool now. The variation between writers is healthy. The variation between AI tools layered on top of writers is the part that fragments brand voice across a quarter.
Most in-house teams run at least one agency for blog, paid, or social, plus a roster of freelancers for spikes. Quality varies across vendors and across the season. A shared scan standard with an Authenticity Score floor gives the team one number to enforce instead of subjective voice notes.
The content lead, the brand director, or the head of marketing owns the bar. Editorial review with the score in hand shrinks from fifteen minutes per article to ninety seconds. The recovered editor time pays for the workflow in the first week.
Five surfaces share one workflow: drafted with AI assistance, edited by a writer, reviewed by the content lead, scanned before publish. Each surface has its own register and its own risk profile when the AI flavour sneaks through.
The blog post a prospect reads before booking a demo. Generic prose signals a generic product, and Google's helpful-content refresh keeps pushing thin AI articles down the SERP. Target an Authenticity Score above 80 on every published article and rewrite the flagged sentences before push. The intro and the closer are the highest-risk paragraphs because both default to stock phrasing when drafting moves fast.
Cold replies depend on conversational prose. A six-email nurture drafted in one AI session reads as one voice across all six, and open rates collapse by message three. Scan the full sequence as a batch before scheduling and vary phrasing per email. Reply rates usually recover within a sequence or two once the scan becomes routine.
Short-form pieces where the chunk is below the classifier's reliable band on a single caption. Batch ten captions together for one scan so the model has enough signal to score consistently. The point is rhythm and concrete vocabulary, not a per-caption number.
Three- and four-line ad units where the AI flavour reads templated even after personalisation. CTR drops on the first refresh and the buyer assumes the offer is the problem. Scan paid creative as a batch the same way as social captions and rewrite the lines flagged at the sentence level.
The hero, the subhead, the bullet list. A flat hero costs click-through to demo, and the second feature block sets the tone for the rest of the page. Scan every landing draft and rewrite the AI sentences before the page ships, especially the hero and the first feature block.
Business at $39.99 a month standard, $29.99 a month on yearly, is the right fit for in-house marketing teams shipping fifty or more assets a month across blog, email, social, paid, and landing. Five shared seats, audit log, REST API, white-label PDFs. Full details on the pricing page.
Billed $89.88/year — Save $30
Billed $179.88/year — Save $60
Billed $359.88/year — Save $120
Yearly billing saves 25%. View full pricing →
Brand voice fragments faster than most marketing leads expect. Five writers leaning on a mix of GPT, Claude, and Gemini produce drafts that drift toward a neutral templated register inside a quarter. The scan is the diagnostic that catches the drift before the CMO does.
Editing catches individual sentences. It rarely catches the aggregate drift across twelve articles in a month, which is why brand voice audits keep returning the same finding quarter after quarter. The scan surfaces the structural drift by showing sentence-level highlights across the whole calendar, not just inside one piece.
A style guide that asks for specific product vocabulary instead of generic SaaS language is also asking for prose that reads less templated. The two requirements collapse into one. Writers honouring the brand vocabulary lift the detector score as a side effect, and the brand stays distinct in the SERP and the inbox.
The Authenticity Score is the diagnostic, not the goal. Rewriting purely to lift the number flattens the voice. Use the sentence highlights to find the specific lines that drift into stock phrasing, rewrite those, and let the headline score land where it lands. The brand voice survives the workflow.
The Business tier gives the team one workspace with shared scan history across writers and deliverables. The content lead pulls a rolling thirty-day view per surface (blog, email, social, paid, landing) and sees averages instead of anecdotes. A surface drifting toward lower scores gets attention before a published asset does.
Most in-house marketing teams run at least one outside agency on blog, paid, or social. Quality varies across vendors and across the season. A shared scan standard with an Authenticity Score floor gives the team one number to enforce instead of subjective voice notes that the agency cannot action.
Most teams settle on a floor of 75 or 80 for agency work. Put the number in the kickoff doc so an agency sending a 72 knows to revise before submitting. The number itself matters less than the consistency: a stable floor across every deliverable signals to the agency that quality control runs the same way every time.
Ask the agency to attach a screenshot of the TextSight scan or the PDF export to every delivery email. Once an agency learns the bar in the first cycle, scans become a normal part of their internal QA and the back-and-forth on voice drops sharply. White-label PDFs on Business let the agency brand the export to their own template.
If the in-house team requests substantive edits, the agency rescans the revised piece and reattaches the report. This catches the case where a revision accidentally drops the score by introducing a flat templated passage to fix a different issue.
The Business audit log shows which writer or agency scanned which deliverable, with timestamps and PDF export records. Useful for quarterly vendor reviews where the marketing lead wants to demonstrate consistent AI quality control across multiple agencies rather than relying on the relationship manager's read.
Five-minute addition per asset. The recovered editor hours and the improved published metrics pay for the workflow in the first week. Integrations are honest about scope: Chrome extension and WordPress plugin ship today, REST API is the path for everything else.
Writers draft in Google Docs, Notion, or the CMS. AI tools are allowed; the scan is the standard, not the prohibition. The team uses ChatGPT, Claude, Gemini, or a mix without restriction. The bar is what gets published, not what gets drafted.
The writer runs a scan in the TextSight web app or hits the Chrome extension inside Google Docs. The score and sentence highlights come back in about six seconds. The writer can revise once before flipping the doc to the editor, which catches most issues before review even starts.
The editor sees the score in the shared workspace and reads the highlighted sentences. Approve if above the team floor; request a rewrite on the flagged passages if below. Editorial review shrinks from fifteen minutes per article to ninety seconds.
The WordPress plugin re-scans the final draft before publish and blocks anything below the floor. The REST API on Business does the same for Sanity, Contentful, Webflow, HubSpot, or a custom CMS via webhook on status change. We do not ship a native plugin for Sanity or Contentful yet, so the API is the integration path for those.
Chrome extension and WordPress plugin ship today. REST API is on Business and covers any CMS via webhook. Native Sanity, Contentful, and HubSpot plugins are on the 2026 roadmap but not live. Most teams add the Chrome extension first, layer in WordPress if they run it, and use the API for everything else.
Two pressures at once. Google weights AI-shaped prose more aggressively each refresh, and readers recognise the templated tone faster than they did a year ago. Pre-scanning is the workflow that keeps the brand on the right side of both ranking algorithms and human readers.
Google's helpful-content updates have weighted AI-shaped prose more aggressively across the 2024 and 2025 refreshes, and thin templated posts keep moving down the SERP. The path through is not avoiding AI assistance; it is publishing AI-assisted content that reads structured and on-register. The scan is the workflow change that makes that possible at volume.
Cold email replies depend on natural conversational prose. AI-flavoured sequences read as templated even when personalised, and reply rates drop within the first send. Run sales sequences through the detector before launch, target an Authenticity Score above 80, and rewrite passages flagged at the sentence level. Reply rates usually recover within a sequence or two.
A flat AI hero costs click-through to demo. The first feature block sets the tone for the rest of the page. Scan every landing draft and rewrite the AI sentences before the page ships. The conversion improvement on borderline landing pages is the metric most teams notice first.
Scans are private to your workspace. We do not share team content with anyone and we do not train the classifier or any other model on submitted drafts. NDAs with outside agencies and confidentiality clauses inside the brand are honoured by default across Free, Starter, Pro, and Business.
More for marketing teams.
The per-writer workflow with delivery-attached scans and brand voice defence.
For writers →Agency-side counterpart for vendors delivering fifty-plus pieces a month into in-house teams.
For agencies →REST API reference for CMS integration: Sanity, Contentful, Webflow, HubSpot via webhook.
Read the docs →Free, Starter, Pro, Business. Yearly billing saves 25%. Business is the team tier.
See pricing →Free to try. No card. Business at $29.99 a month on yearly for in-house marketing teams shipping fifty or more assets a month.