Photograph a document. Get the numbers back.
Point your phone at a receipt, an invoice or a statement. You get the text with its tables intact, and the fields you asked for by name — each one shown against the page it came from, so you can check it before you trust it.
Straighten it, crop it and clean it up on the phone before it is ever sent. Your scans stay in your account, searchable, grouped by where you took them.
Two things we do
Upload one page and see for yourself, or read the pricing.
Document parsing — layout
Markdown, real <table> HTML with rowspan and colspan intact,
and every region typed with its pixel box. Measured at 0.912 TEDS
on OmniDocBench — level with the published state of the art.
Field extraction — fields
Name the fields you want and get them back as key/value pairs:
1 as lastname, [due date] as due, or
if it is a driver license: …. Included on every plan.
Built for a phone
The camera, the crop box and the clean-up all run on the device. A photo is straightened and shrunk before it leaves, so a scan works on the shop floor and not just on the desk.
Kept, not dumped
Every scan stays with your account for as long as your plan is active, and for at least 90 days after you cancel. Search them, group them by where they were taken, or export a batch as CSV or JSON.
Whole documents
PDFs are rasterised a page at a time, so a 500-page file does not need 500 pages of memory.
How it works
- Sign in and open the workspace — on a phone it opens the camera.
- Photograph the document, or drag a stack of files in. Pick the output you want, and for fields, name them.
- We read every page and give you Markdown, JSON and a CSV of the fields.
Access is currently invite-only while capacity is limited.