Document data extraction
Extract the data you need from any document.
Invoices, receipts, contracts and forms. Define your fields once; Parsevix reads every document, finds them, line items included, and returns clean structured data to your app.
- Your own fields and line items, not a fixed template
- PDF, Word, scans and photos, in many languages
- Personal data masked automatically before the AI step
No credit card · 20 free credits every month
One messy inbox in.
Your own piles out.
You name the categories, as specific as your work needs. Parsevix puts every document on the right pile, then reads the fields that pile asks for.
From the first e-mail to your app, without retyping a thing.
Parsevix collects your documents, sorts them into your categories, extracts your fields and hands clean data to the tools you already use.
Upload in the dashboard, forward e-mails to your project's own address, or send files through the API.
Plugs into
10,000+ apps.
Every finished document can land in your accounting, CRM, spreadsheets or chat the moment it is done. Through Zapier with no code, or straight into your own system.
Security & compliance
- PII maskedautomatically, before the AI step
- Encryptedin transit and at rest
- No AI trainingon your documents
- API files deletedafter processing
FAQ
Questions,
answered.
The short version of what people ask before they upload their first document.
PDF, Word (DOCX), PNG, JPG and TIFF, up to 10 MB and 30 pages each. Scans and phone photos work too: every page is read as an image, and sideways or upside-down pages are turned first.
No. Create a category, name the fields you need and add a table for line items. Or skip that: Parsevix can pick the category for you, or pull out every field it finds.
Latin scripts, Cyrillic, Greek, Arabic, Chinese, Japanese, Korean and more. The language is detected per page, so you don't choose it, and your fields stay the same whatever the document is written in.
Every value is linked to the spot on the page it came from. Click it and the page shows you where it was printed. If a value is wrong, reject the document with a reason or run it again.
Names, addresses, bank details, ID numbers and other personal data are detected automatically and masked before any text goes to an AI model, then put back in your result. Detection is automatic: it catches most personal data, but not necessarily every item. If masking fails, the document stops there. Your documents are never used to train AI.
Through the REST API, where the data comes back in the same response; by signed webhook; or through Zapier into thousands of apps. Documents can also come in by e-mail to your project's own address.
One credit per page; choosing the category is included, and sorting a document without extracting it costs 1 credit. The Free plan has 20 pages a month with no credit card. Paid plans start at $39 a month for 500 pages and add e-mail inboxes, more projects and higher limits.
Yes. Delete a document, a whole project or your account at any time, and the files go with them. Files sent through the API are deleted after processing unless you turn on keeping them.