Redact a PDF the right way.
Drop a document and the AI proposes redaction boxes for names, ID numbers, dates of birth, addresses, and account numbers - drawn on the real pages so you can check every one. Download is burned in, not a cosmetic black box. Free, no signup.
Burned in, not covered up
A black rectangle is not a redaction
The redaction failures that make the news share one mechanic: a drawing tool placed an opaque box over live text, and anyone could select underneath it. This tool produces a flattened file - the masked pixels are gone and the text layer under every box is removed - so what you release is what a reader gets.
Pixels masked
The redacted regions are rendered out of the page image itself.
Text layer removed
No copy-paste, no find-in-page, no hidden layer for the content under a box.
Same engine as the platform
Detection uses the extraction engine DocuPipe customers run on claims files and medical records.
Enterprise: in-cloud deployment
Redaction that never leaves your building
Redaction is the workload where "send it to a SaaS" is often the wrong answer by policy, not by preference. The documents being redacted are, by definition, the most sensitive ones an organization holds - patient charts, claim files, investigative records, personnel matters. For many hospital systems, insurers, and public agencies, the data-handling rule is simple: it does not cross our boundary.
DocuPipe was built for exactly that rule. For enterprise commitments, the entire platform deploys into your own cloud account: the API, the OCR engine, the extraction and redaction models, the workers, and the storage all run inside infrastructure you control. Nothing - not the documents, not the extracted text, not the redaction boxes - leaves your environment. Installation is a single command, and a green install includes a live end-to-end test.
Your cloud, your keys
Runs in your AWS, Azure, or GCP account with your access controls, your logging, and your retention rules.
Full containment
API, OCR, models, workers, and storage - the whole pipeline, not a thin proxy that still phones home.
Same product, same reviews
Your team gets the identical workflows and review screens the SaaS runs - just inside your walls.
Teams without an in-environment requirement run the same redaction on DocuPipe's cloud, which carries the posture this page runs on: SOC 2 and ISO 27001 certified, HIPAA compliant, encrypted in transit and at rest, documents never used for training, and BAAs executed on paid plans.
The same presets, tuned per profession
The category presets map onto how each release desk actually works. Pick the ones that match your job, add your own rules in plain language, and the same engine follows them.
HIM / release of information
Producing records with other patients, family members, or restricted information in the margins - names, MRNs, DOBs, and member IDs are the daily categories.
FOIA and public records
Personal-privacy withholdings on responsive records: requester-adjacent names, home addresses, personal phone numbers, and identifiers - before anything hits the reading room.
DSAR and privacy teams
Producing one person's data means removing everyone else's. Third-party names and contact details are the default categories for a subject-access response.
The sample documents above are fictional and free to reuse in training material - link to them directly: Medical record (PDF) · Incident report (PDF)
Questions records and privacy people ask first
Really removed. The downloaded file is a flattened PDF with the redacted pixels masked and the underlying text layer removed - there is no live text under the boxes to copy out. That distinction is exactly where cosmetic-overlay redactions have failed people in public.
Yes, and the tool is built to make that easy rather than to let you skip it. Automated detection is an assist: it can miss context a human would catch, so the review screen shows every proposed box on the real page before anything is downloadable.
Use it as the first pass, not the sign-off. No automated tool can guarantee a legally compliant release - your reviewer makes that call. The infrastructure side is covered: SOC 2 and ISO 27001 certified, HIPAA compliant, encrypted in transit and at rest, and documents are never used to train models.
Adjust the categories or add plain-language instructions ("redact all vehicle plate numbers") and re-run - detection follows your guidelines. Whatever it proposes, the review screen is where you verify before release.
The free tool reads the first 10 pages of a document per run - redaction runs a heavier AI pass per page than plain extraction, so its cap is tighter than our other free tools. A free DocuPipe account raises the limits substantially.
Yes. For enterprise commitments, DocuPipe deploys the entire platform - API, OCR engine, extraction models, and storage - inside your own cloud account, so documents never cross your boundary. See the in-cloud section on this page.
That is the product behind this tool: DocuPipe workflows run redaction on every document that arrives - by API or upload - with your presets applied consistently and your team reviewing in one place.
Run it at scale
Redacting one file is a chore. Redacting everything your team releases is a workflow.
Release-of-information desks, FOIA offices, and claims teams run redaction on a queue, not a file. DocuPipe applies your redaction rules to every inbound document automatically and gives reviewers one place to verify and release.
Free tier included. Takes about a minute to set up.
SOC 2 certified · ISO 27001 · HIPAA compliant · Encrypted in transit and at rest · Never used to train models