Adobe PDF Accessibility Auto-Tag API
Cloud API that adds structure tags to PDFs at scale, as a first step towards accessibility.
Jobs Accessibility
Opens the vendor's own site.
Jobs covered
Open a task to see exactly what the vendor documentation supports.
Accessibility
Browse all accessibility toolsautomatically tagging PDFs to add document structure, replacing any existing tags, with an optional report on the added tags, through the REST-powered PDF Accessibility Auto-Tag API in the Adobe PDF Services API, where the tagged output is not guaranteed to comply with WCAG or PDF/UA without further remediation
Where your files are processed
Reported to upload your files
The vendor states that files are uploaded to their servers. We have not independently tested this.
A cloud API: the document is uploaded to Adobe Document Cloud, processed there, and the tagged result is downloaded. Adobe's security documentation states that server-side components of the PDF Services API are processed in Document Cloud on AWS infrastructure in the US-East and EMEA regions, and that uploaded assets and generated output are stored for 24 hours by default.
The REST flow also supports external storage and immediate deletion of assets, which the Java SDK exposes.
What it does
This is an API that reads an untagged PDF and writes a tagged one: headings, paragraphs, lists, tables and language, plus a spreadsheet report describing what it decided. It is meant for backlogs - thousands of documents that were never tagged - and it will replace whatever tags already exist, so it helps most where there are none or they are poor.
Adobe is explicit that the output is a starting point rather than a finished accessible document, and that alt text, complex tables and reading order still need a person.
Best for
Organisations with a large archive of untagged PDFs who need the mechanical work done automatically, and developers adding an accessibility step to a document pipeline. It tags through an API rather than a document at a time, which suits a pipeline or a backlog.
Equidox documents API-integrated batch remediation as well, so it is not the only route to that in this index.
Worth knowing
It replaces existing tags rather than improving them, so running it over documents that have already been worked on can destroy remediation that a person did by hand - a real risk for anyone pointing it at a mixed backlog. It also does not produce a compliant document and says so: the tagged output is not guaranteed to meet WCAG or PDF/UA, and the remaining work is exactly the work that is hard to automate - alternative text for every figure and a review of complex tables, plus checking how the title was identified and whether the reading order survived.
Budget for that second pass or the documents will be tagged and still unusable. Being a cloud service, every document is uploaded, and Adobe's own documentation says assets are held in Adobe Document Cloud for 24 hours by default; for a confidential backlog that is a decision, not a detail.
Details, and where each comes from
Vendor statements, our own reading of their pages, and the things nobody has established yet, each answered separately. Where we have not confirmed something it says so rather than guessing, and a row nobody has established is greyed out.
- Versions covered
- API
- Website
- developer.adobe.com
- Requires an account
- Not verified
- Free tier
- Yes
- Watermark on the free tier
- Not verified
- Maximum file size
- Not verified
- Batch processing
- Yes
- Data residency
- Multiple regions
- Open source
- No
- Self-hostable
- No
- Licence
- Commercial; part of the Adobe PDF Services API
- Redaction
- No redaction feature
- Programmatic access
- HTTP API
- Last availability check
- Responded in 55 ms 21 October 2026
Checked automatically by our own runner, not reported by the vendor. 100% of our last 30 checks got a response.
What the redaction verdict rests on
From the vendor's own documentation, read 22 September 2026. Not tested by us.
“Automatic tagging is a good first step on a document's journey to full accessibility. It outputs the tagged pdf, along with an optional report providing detailed information about the added tags.”
What that does not establish
Recorded as `none` on absence: this service adds structure to a document and never removes content from one. Nothing in its documentation describes redaction.
What it does not establish is that the output is safe to publish - and there is a specific trap worth naming, because it is the opposite of a redaction risk: the service REPLACES any existing tags, so a document whose tagging was carefully remediated by hand comes back with machine-generated tags instead. That is a way to lose work, not to leak data, but on a confidential document both matter.
https://developer.adobe.com/document-services/docs/overview/pdf-accessibility-auto-tag-api/
What the vendor says
Claims are labelled rather than repeated as fact. Where we have checked something ourselves, it says so and shows when. Checked means we read the vendor's own page and it says what we recorded - not that we tested the behaviour, unless the note says we did.
-
“PDF Accessibility Auto-Tag API is a powerful tool that may be used as part of the process of improving accessibility in individual PDFs and can be applied at scale for large backlogs of PDFs. Part of the Adobe PDF Services API offering, it is available as a REST-powered SDK with underlying Sensei AI and is easily called by automated workflows.”
Checked by us - the source says this Read 1 October 2026
Confirmed. The quoted text appears in the rendered page as read on 2026-10-01.
This claim was carried as reported rather than checked until this read.
Standing: Not re-read against the live source
Check it yourself: the source, the SHA-256, and how we checked
- From
- the text a browser renders
- SHA-256
- 7cf2d1dd33b6d723669076aa94eeb394b7529e0b49871219fe9cd595e0843ac0
How we checked
Read as rendered text in headless Chrome on 2026-10-01 and saved to the evidence archive, so the read can be repeated against the same file. Comparison ignores case, punctuation and hyphenation, which is why "open-source" on the record matches "open source" on the page.
-
“The output is a tagged PDF, however it is not guaranteed to comply with accessibility standards such as WCAG and PDF/UA, as you may need to perform further downstream remediation to meet those standards.”
Checked by us - the source says this Read 1 October 2026
Confirmed. The quoted text appears in the rendered page as read on 2026-10-01.
This claim was carried as reported rather than checked until this read.
Standing: Not re-read against the live source
Check it yourself: the source, the SHA-256, and how we checked
- From
- the text a browser renders
- SHA-256
- 7cf2d1dd33b6d723669076aa94eeb394b7529e0b49871219fe9cd595e0843ac0
How we checked
Read as rendered text in headless Chrome on 2026-10-01 and saved to the evidence archive, so the read can be repeated against the same file. Comparison ignores case, punctuation and hyphenation, which is why "open-source" on the record matches "open source" on the page.
Each claim is quoted from the vendor's own pages. This section describes what we have and have not checked - it is not a judgement about anyone.
Sponsorship is distribution, not an endorsement or a promise of search rankings, AI citations, traffic, or sales. This listing is a free entry, compiled from published sources.
Related reading
- Checking a PDF for accessibility - what makes a PDF accessible, and how it is checked.