Free Font Identifier
Font Identifier finds the font in a screenshot or photo. Frame the text, check the characters that text recognition proposes under each letter, and the tool compares their shapes and proportions with 1,576 free Google Fonts families in your browser. It lists the 20 closest families with your text drawn in each and a link to the font.
- Catalog:
- 1,576 Google Fonts families
- Characters:
- A–Z, a–z and 0–9
- Results:
- 20 closest fonts with previews
- Price:
- Free
- Runs:
- Locally, in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
Is my picture uploaded?
No. The letters are found and compared in your browser. The tool downloads the font shapes it needs from this site; those requests only name characters and font families, never the picture.
Can it identify commercial fonts?
Not by name: the catalog has 1,576 free Google Fonts families. For a commercial font it lists the free families whose letters are closest.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Font Identifier
- Drop a screenshot or photo of the text, then use Left, Right or Straighten if the line isn't level.
- Drag the frame around one or two words: the letters found appear below, with the characters proposed by text recognition.
- Check the character under each shape; fix the wrong ones and leave joined or broken shapes empty.
- Click Identify font, compare the previews of the closest fonts and open the one you like on Google Fonts.
Credits & open source
Our own code plus open-source libraries. Thank you to the people who make these projects.
- Tesseract.jsTesseract OCR engine compiled to WebAssembly. © Project Naptha (Jerome Wu, Kevin Kwok, Guillermo Webster); Tesseract OCR by Google and contributors · Apache-2.0
Web platform APIs used: Canvas 2D, createImageBitmap, Pointer Events, Keyboard Events, File API, Clipboard API, Web Workers, WebAssembly.
- Google Fonts (1,576 families, Regular style, letters A–Z, a–z and digits) by The designers of each family, as credited on Google Fonts; files from Fontsource (OFL-1.1, Apache-2.0 or UFL-1.0 (per family)) — letter shapes, boxes and outlines compared with the picture and drawn in the previews (public/fontid)
- tessdata (best_int LSTM model, English) by Google / Tesseract OCR contributors (Apache-2.0) — proposes the character under each letter, when Read the letters automatically is on
Full license texts: third-party notices · all credits
Frequently asked questions
How many letters do I need?
One is enough to start, but the more different letters you check, the better the ranking. Leave out shapes that join two letters or are broken in pieces.
Why is bold or italic text matched poorly?
The catalog has the regular style of each family, so bold or italic letters are compared with regular ones: the closest families get a lower similarity.
What does the similarity mean?
It comes from the differences between the shapes and proportions of your letters and the font's: 100% would be identical. Use it to compare the results of one search, not as a probability.
Does it work with light text on a dark background?
Yes. The background is the color that covers most of the border of the frame, so light text on a dark background is read too.