About Text Recognition in Keep It
Keep It will perform text recognition on PDF documents and images, including attachments on notes, rich text documents, and mail messages.
Text recognition may take some time — see below for more details.
PDF Documents
For PDFs, Keep It will not perform text recognition if the document contains indexable text. Instead, the text stored will be extracted and indexed so that it can be searched.
After performing text recognition, Keep It does not modify PDF documents to add an invisible text layer, but instead indexes that text so it can be searched. The text is also stored in iCloud, if in use, to avoid repeating that work on other devices.
Larger PDF documents and those with more complex layouts may take some time. While it might take a few seconds to recognize the text on a single page, larger and more complex documents could take a few minutes.
Keep It always performs text recognition in the background (and on Mac, in a completely separate process). To see progress on Mac, choose Window > Activity from the main menu and check whether Keep It is performing any “Extracting info” operations. On iOS or iPadOS, tap (…) above the list of items and choose Show Activity from the menu shown.
Images
For images, Keep It uses computer vision to detect areas of text in the image, and only performs text recognition on any areas found.
As with PDFs, image files are not modified, but rather the text is indexed so that it can be searched, and stored in iCloud (if in use) to avoid duplication of work across devices.
Text recognition for images may not be as accurate on macOS 10.13 High Sierra and iOS 11 as on macOS 10.14 Mojave and iOS 12 or later, due to advancements in Apple’s computer vision technology.
Screenshots
Text recognition works best with higher resolution images such as photos, and for text where there is a high contrast between foreground and background colors. Screenshots may produce good results unless the screenshot was taken from a higher resolution screen, such as a Retina display.
Attachments
Keep It will perform text recognition if necessary on attachments to notes, RTFD files, and mail messages.
Languages and Scripts
Text recognition relies on knowing which language it needs to recognize. By default, Keep It uses the same language as your Mac or iOS device. On Mac, this can be changed to another language, or a script that encompasses many related languages (e.g. Latin).
Preferred languages can be set in Language & Region System Settings on Mac, or General Settings on your iOS device.
Keep It for Mac
Keep It for Mac can use one of two text recognition engines: Vision, which is part of macOS, or Tesseract, which is much slower and often less accurate. Keep It will use Vision if your primary language is supported, and will include any secondary languages that are also supported:
- macOS 11 and later includes English, Chinese, Portuguese, French, Italian, German and Spanish.
- macOS 13 and later also includes Cantonese, Korean, Japanese, Russian and Ukrainian.
- macOS 14 and later also includes Vietnamese and Thai.
- macOS 15 and later also includes Arabic.
- macOS 26 and later also includes Turkish, Indonesian, Czech, Danish, Dutch, Norwegian, Malay, Polish, Romanian and Swedish.
- macOS 27 and later also includes Finnish, Hindi, and Marathi.
For other languages or scripts, Tesseract will be used with only the primary language or script. However, most scripts also include support for English, except Cyrillic.
For handwriting recognition, only Vision will likely produce usable results.
To change the language or choose a script:
- On Mac, choose Keep It > Settings from the menu
- Click Search
- Choose the language or script using the pop-up.
Keep It will offer to reindex documents when the language is changed.
Keep It for iPad and iPhone
Since version 2.9, Keep It for iPad and iPhone only uses Vision for text recognition, and the supported languages are as follows:
- iOS or iPadOS 14 and later includes English, Chinese, Portuguese, French, Italian, German and Spanish.
- iOS or iPadOS 16 and later also includes Cantonese, Korean, Japanese, Russian and Ukrainian.
- iOS or iPadOS 17 and later also includes Vietnamese and Thai.
- iOS or iPadOS 18 and later also includes Arabic.
- iOS or iPadOS 26 and later also includes Turkish, Indonesian, Czech, Danish, Dutch, Norwegian, Malay, Polish, Romanian and Swedish.
- iOS or iPadOS 27 and later includes Finnish, Hindi, and Marathi.
On iOS and iPadOS, Keep It will temporarily download items to perform text recognition while the app is connected to Wi-Fi (unless the "Use Mobile Data for Indexing" setting is enabled in Keep It’s Settings). Text recognition is not performed in Low Power Mode.
Disabling Text Recognition
Text recognition can be enabled or disabled on a per-device basis. To disable text recognition:
- On Mac, choose Keep It > Settings from the menu, then click Search. Disable the “Recognize text in PDFs and images” option.
- On iOS, tap the gear icon above the Lists view, then tap on Text Recognition, and switch “Recognize Text in PDFs and Images” off.