Images

Image to Excel: turn a picture of a table into a spreadsheet

A photographed table, as a spreadsheet.

On this device

Choose a picture of a table

One picture, or a one-page PDF, cropped to the table if you can. The reader downloads once, about 660 MB, and stays in this browser.

    Opened on this device · never transmitted

    What this tool does, exactly

    A screenshot, a scan or a photo of a table goes in; an .xlsx with the same rows and columns comes out, plus the table as Markdown. The reading is done by a vision-language model in this tab, on your graphics card — it needs a laptop or desktop and about fifteen to forty seconds, and it is behind the Pro door, free during the preview.

    What it does
    Hands the whole picture to GLM-OCR, a 0.9-billion-parameter vision-language model, with the instruction to recognise a table. It answers with the table's structure — header, rows, cells, merged cells — which becomes a worksheet through this site's own spreadsheet writer, the same one PDF to Excel uses. Numbers become numbers; everything else stays text.
    What it refuses
    A phone or tablet, a device with under 8 GB of memory, a browser without WebGPU, a graphics chip too small for the model, a document of more than one page, and a picture the model does not read as a table — in that last case it says so and points at the Deep reader on Image to text and the fast reader, rather than inventing rows.
    What it costs
    About 660 MB the first time, from Hugging Face's servers, kept in this browser's cache afterwards; then fifteen to forty seconds a table on a recent laptop, measured 39 seconds for an A4 invoice on an Apple M4 Mac. Two to three gigabytes of memory while it runs.
    Why crop first
    Not for time but for structure: a cropped table is read at higher resolution for the same seconds, and on the one invoice measured the whole page came back with its totals block sideways where the crop came back right. The scanned-invoice page carries the measurement.
    Why Pro
    The button shows a price and then tells you the preview is free. The price is a question — would anyone pay for a reader this heavy? — and the click is the answer. No card, no account, nothing charged.

    About this tool

    How accurate is it?

    On a clean picture of a printed table, in testing, the reader read an eight-row invoice with every cell right, header and totals included. On a phone photo taken at an angle, or a table with faint rules and wrapped cells, expect merged or shifted cells and check the sheet against the picture. The Markdown beside the spreadsheet is there for exactly that comparison.

    Why is it so much heavier than the other OCR tools?

    The fast reader finds lines and reads them, which is enough for text and costs six megabytes. Keeping a table as a table means understanding the page's layout, and the smallest model measured that does it honestly in a browser is 660 MB. That is the weight of rows and columns, and it is downloaded once per browser.

    Does the picture leave my device?

    No. The model is downloaded to this browser; the picture is read here. The only outside request is for the model's own files, from Hugging Face, pinned to one version and checked against digests this site carries. What that request contains is on the privacy page.

    Can it read a table out of a scanned PDF?

    A one-page PDF, yes: the page is drawn and read as a picture. For a multi-page scan, use OCR a PDF's Deep mode, which reads every page as Markdown with its tables as rows of cells, or export the page you need with PDF to image and bring it here.

    What does Pro cost?

    Nothing during the preview. The Pro door shows a price because we want to know whether a reader of this weight is worth paying for; behind it there is no checkout, no card and no account. If a paid tier ever exists, it will be a new page that says so, not a change to this one.

    More images tools · All 52 · How they work