Best forText in images and non-selectable interfaces
ResultRecognized copyable text
InternetOptional for Microsoft OCR or online translation

What Screenshot OCR does

Capture a region without first selecting text. On-device recognition runs locally and attempts to preserve paragraphs, lists, and table-like columns; review the result for errors. In 2.3.0, screenshot mode starts explicitly, with no idle OCR mouse interceptor or hold-and-drag gesture.

How to use it

  1. Start Screenshot OCR with a two- or three-key combination, the ActionClip status menu, or the widget action.
  2. Drag over the screen region containing the text. Press Escape or right-click to cancel.
  3. Edit and copy the recognized text, or use direct-to-clipboard mode.

Example

Screen region

Invoice 12345 Total: $42.00

Recognized text

Invoice 12345 Total: $42.00

Settings

Open the action's settings from:

ActionClip → Actions → Screenshot OCR → gear

Result

Choose whether recognized or translated text opens in a result popup or is copied directly.

  • Show Result Popup
  • Copy to Clipboard

Capture controls

Record a two- or three-key combination to enter screenshot mode. The old hold gesture is removed.

  • Keyboard shortcut

OCR model

Choose local recognition or send the captured region through ActionClip to Microsoft.

  • On-device — Recommended
  • Microsoft — Online

Playback

Optionally show Play, Pause, and Resume for recognized text.

  • Show Play button
  • Speech voice

Translation

Enable Auto translate and choose Translate to. Uses the Translate action’s provider, with a separate target language for OCR. Recognition accuracy and result destination remain independent. Online translation sends recognized text to the provider; on-device recognition stays local.

Changes are saved automatically.

You can also replace this action's icon from ActionClip → Actions. See change an action icon.

When ActionClip suggests it

Available whenever enabled and does not require an existing text selection.

Enabled actions remain available in your Actions list even when Smart Suggestions do not promote them for the current selection.

Requirements and privacy

  • This guide describes ActionClip 2.3.2 or later. Configure a new shortcut when upgrading from the old hold gesture.
  • macOS may request Screen Recording permission before capture. Use Open Settings in a permission error, then restart ActionClip if macOS requires it.
  • On-device recognition runs locally and does not require Online Actions. Disabling OCR or pausing ActionClip immediately cancels capture.

Cut line breaks and restore

Cut line breaks joins wrapped OCR lines while retaining paragraph breaks. In the result popup, Restore original text returns the recognized layout. Cleanup works independently of Balanced or More Accurate recognition and optional translation.

Copy Copy sends the current selection to the Mac clipboard without changing the source text. Paste Plain Paste Plain removes rich formatting so text can be inserted or reused without the source font, color, or styling.

Choose on-device or Microsoft recognition

In ActionClip 2.3.6, open Actions → Screenshot OCR → gear → OCR model. On-device — Recommended recognizes the captured region on your Mac. Microsoft — Online sends the image of that region through ActionClip’s service to Microsoft for recognition.

Microsoft recognition requires Allow online actions; when online actions are off, ActionClip uses Apple OCR on this Mac. On-device recognition improves handling of small text, but both providers can make mistakes. Capture a clear region and review names, numbers and formatting.

Recognition and translation are separate choices. Enable Auto translate to translate the recognized text with your translation provider. The result popup shows the original recognition and translated text together. Online translation sends the recognized text to that provider, independently of your OCR model.

Back to all built-in actions