Skip to content

FAQ

Frequently asked questions

If your question is not here, the security page covers how we handle data in more detail, and the API reference covers everything programmatic.

How long do you keep my statements?

Nothing is uploaded, so there is nothing for us to keep. Conversion runs inside your browser and the extracted rows live in the page until you close it. We never receive your statement, so it cannot be stored, trained on, or handed to anyone.

Do I need an account?

No. Without an account you can convert 1 page every 24 hours, and signing in with Google gives you 5 free pages. Pay As You Go credits ($0.10/page, from $5 for 50 pages) can be bought without an account too: they are saved in your browser, and signing in with Google later moves them onto your account so they work on any device. Pro ($10/mo for 200 pages) needs a Google sign-in, because a subscription is managed from your account.

Is my financial data used to train models?

Never. Your documents are processed to produce your output and then deleted. They are not used for training, not sold, and not shared with third parties.

What if my statement is password protected?

Enter the password in the prompt that appears next to that file. The document is unlocked in place — the rest of the batch is untouched, and anything you have already corrected stays corrected. Each file gets its own prompt, so a batch with different passwords is fine. The password is used once, in memory, and is never stored or logged.

How accurate is the extraction?

On clean text-based statements from supported banks, typically above 99% at the row level. Every row carries a confidence score, rows below 90% are flagged for review, and the balance check tells you whether the whole statement reconciles against its opening and closing balances.

What does the balance check actually do?

It adds your opening balance to the sum of every extracted transaction and compares the result to the closing balance printed on the statement. If they match, nothing was missed or double-counted. If they do not, we tell you by how much so you can find the bad row.

Can I fix a row the parser got wrong?

Yes. Every cell in the results table is editable, and you can delete rows entirely. Your edits are what gets exported — the download is generated from the table you see, not the original extraction.

Do you support scanned or photographed statements?

Text-based PDFs, which is what banks issue, work best and are what our accuracy figures describe. Scans without a text layer are not currently supported — we will tell you rather than return quietly wrong numbers.

Which banks do you support?

80 banks across 19 countries are recognised by name, including the major retail banks in the US, UK, Canada and Australia. Recognising a bank tells the parser how its country writes dates and amounts. A statement from any other bank usually still converts, because the parser reads the layout of the page rather than a template. The full list is on the Supported banks page.

Can I use this from my own code?

Not yet. The conversion engine has an HTTP interface and the contract is documented, but it is not currently offered as a hosted service, so there are no API keys to issue. Conversion today happens in the browser. If you need programmatic access, get in touch and tell us what you are automating.

Still stuck?

Send us the bank and a description of what came out wrong — not the statement itself.

Contact support