Desktop
For one person converting scans
$149per workstation, per year
- Command-line program
- Searchable PDF, JSON, hOCR, ALTO, text
- GPU acceleration
- Local HTTP service
- Library for your own software
OCR for scans, PDFs and handwriting · runs offline
Every word read, boxed and scored.
Glyphwise turns scanned documents into searchable PDFs and structured text on your own computer. Every word comes back with its position on the page and a confidence score, so you know which ones to check.
Windows 10 and 11 (x64). One-time install, no account, no internet connection needed.
Worksheet 2.
Funds Belonging to the Person
1. Enter the total funds received . . . . . 1.
2. Amount used for the person’s support
3. Add lines 1 and 2 . . . . . . . . 3.
{ "text": "Belonging", "confidence": 0.99,
"bbox": { "x": 412, "y": 318, "width": 236, "height": 52 } }
{ "text": "person’s", "confidence": 0.62, ← flagged for review
"bbox": { "x": 1180, "y": 514, "width": 218, "height": 49 } }
What it reads and writes
Feed it the files you already have.
PDFs with a text layer are read directly, without OCR, so born-digital documents come back exact. Scanned pages and phone photos are repaired first: crooked, sideways and upside-down pages are set straight, a page photographed at an angle is flattened, and shadows and speckles are cleaned away.
Input
- PDFText layers read directly; scanned pages recognized. Archive.org-style MRC scans supported.
- TIFFMulti-page; uncompressed, LZW, Deflate, PackBits, CCITT G3/G4, JPEG.
- JPEG 2000, JBIG2Including the formats used inside library and archive PDFs.
- PNG, JPEG, GIF, BMP, PNMPhone photos of pages (straightened and evened out) and screenshots.
Output
- Searchable PDFYour scan with an invisible text layer: search, select and copy.
- JSONPages, blocks, lines and words, each with a box and a confidence score.
- hOCR, ALTOThe standard formats for digitization, library and archive systems.
- Plain text, review listText for indexing, and a spreadsheet of the words worth checking.
Measured, not claimed
Fewer errors on real documents.
We test on public-domain government documents, forms and handwritten archives that the models never saw in training, and compare with Tesseract, the most widely used open-source OCR engine.
| Test set | Measure | Glyphwise | Tesseract 5.4 |
|---|---|---|---|
| Government documents2,000 lines from 8 held-out documents | character errors | 0.28% | 1.47% |
| Full pages, forms included38 pages: Federal Register, IRS forms, NIST report | words found (F1) | 97.3% | 94.1% |
| Second page set53 pages from 27 other held-out documents | words found (F1) | 97.7% | 94.0% |
| Phone photos of pagesthe same 38 pages, photographed at an angle, in uneven light, slightly blurred | words found (F1) | 96.5% | 90.9% |
| Handwritten manuscriptsBentham papers, 18th–19th century | character errors | 13.5% | 74.7% |
| Speedthe 38 pages above, laptop with an NVIDIA GPU | total time | 13 s | 21 s |
Lower is better for errors, higher for words found. Pages rendered at 300 dpi; Tesseract with its standard English model. Glyphwise numbers are for the model that ships with the product. Words found counts every word the page's text layer holds, punctuation, dot leaders and form labels included; much of the gap comes from those, which Tesseract often leaves out. Counting only words with a letter or digit, Glyphwise still leads (98.0% vs 97.7% and 98.1% vs 97.2%). Handwriting is harder for every engine: expect noticeably more errors than on print. The photo copies are generated from the test pages (perspective, shadow, blur, lower resolution, JPEG and noise combined), so the ground truth is exact.
Three ways to run it
From one folder of scans to your own application.
Command line
Batch-convert folders. Files are processed in parallel; add --gpu to use an NVIDIA card.
glyphwise models\line.bin *.tif ^
--pdf searchable.pdf
Local service
An HTTP service for your document system or scanner workflow. It stays on your network.
curl --data-binary @scan.pdf ^ "localhost:8080/ocr?format=alto"
Library
A DLL with a small C API, callable from C, C#, Python, Go or anything with a C interface.
char *json = glyphwise_recognize(
h, bytes, len, 0);
Your documents stay yours
Nothing leaves your machine.
Contracts, medical records and tax forms are exactly the documents that should not be uploaded to someone else’s cloud. Glyphwise never connects to the internet.
No cloud processingRecognition runs entirely on your computer or server.
No telemetryThe software sends nothing: no usage data, no crash reports.
No activation serverYour licence is a signed file checked offline. It works on air-gapped machines.
Built in-houseThe recognition engine and models are our own, with no third-party OCR inside.
A quiet website, tooNo cookies, analytics or trackers here; fonts are served from this site. See the privacy notice.
Clear termsAnnual licences, no automatic renewal, 30-day refunds. See the terms of sale.
Pricing
Pay per licence. Keep your data.
Each licence runs for one year and includes every update released in that year. Prices in US dollars, before applicable tax.
Server
For a team or a document workflow
$990per server, per year
- Everything in Desktop
- Local HTTP service for your internal systems
- Unlimited users inside your organisation
- Email support
- Library for your own software
Developer
For building OCR into internal applications
$2,900per site, per year
- Everything in Server
- DLL and C API with header files
- Up to 5 developers at one site
- Priority email support
Shipping Glyphwise inside your own product, or offering it as a hosted service?
That needs a distribution licence. Write to us with what you are building and roughly how many
customers it will reach.
Contact sales
Free evaluation
Try it on your own documents first.
- Download the evaluation package and unzip it. No installer, no account.
- Run
glyphwiseon a few of your own scans. Without a licence it reads up to 3 pages per run, with every feature switched on. - When you buy, your licence file arrives by email. Put
glyphwise.licnext toglyphwise.exeand the limit is gone.
Download for Windows
Includes the user guide, licence agreement and third-party notices.
Questions
Before you buy
Which languages does it read?
English and other languages written in the Latin alphabet without many accented letters. The language model that corrects likely misreadings is trained on English, so English gives the best results.
Does it need a graphics card?
No. It runs on any modern x64 processor and uses all its cores. An NVIDIA card (or any OpenCL card) makes large batches faster; the results are identical either way.
How good is it on handwriting?
Much better than engines built only for print, but handwriting is still hard: on 18th-century manuscripts about one character in eight is wrong, and casual modern handwriting photographed on a phone is harder still. Use the confidence scores and the review list to find the words to check.
What happens when my licence expires?
The software goes back to evaluation mode (3 pages per run) until you renew. Files you already converted are yours and are not affected.
Can I get a refund?
Yes. If Glyphwise does not work for you, ask for a refund within 30 days of purchase. See the terms of sale.
Do you support Linux or macOS?
The packaged release is for Windows. A Linux build is available on request for Server and Developer licences.
Can it read photos taken with a phone?
Yes. Pages photographed at an angle are found and flattened, sideways and upside-down photos are turned upright, and shadows are evened out. For best results photograph the whole page, flat, in even light, against a darker background.
Where is the documentation?
The user guide covers installation, the licence file, the command line, the HTTP service and the C API. It is also in the download.