For the complete documentation index, see llms.txt. This page is also available as Markdown.

Screenshots, Annotations, and OCR

Cherry Studio can capture a screen region with a global hotkey, add rectangles, arrows, brushes, text, or mosaics, and copy or save the result. After enabling local OCR, you can also directly select and copy text in the screenshot.

Goals and prerequisites

  • Path: [Settings] → [Screenshot];

  • On macOS, you need to allow Screen Recording the first time you use it; after authorization, restart the app as prompted on the page;

  • OCR requires downloading a text recognition model in [Settings] → [Local Models];

  • The screenshot feature is disabled by default, and automatic text recognition is enabled by default, but OCR will not run if the model is not ready.

Terms

Terms
Meaning

Global hotkey

A hotkey that can be triggered even when the current focus is not in Cherry Studio

OCR

Recognize text in an image as selectable, copyable text

Mosaic

Obscure accounts, paths, keys, or other sensitive areas in the screenshot

Operation path

[Settings] → [Screenshot] → turn on [Enable Screenshot] → press the screenshot hotkey → select an area → annotate or recognize text → copy or save.

Steps

1

1. Enable screenshots and check permissions

Open [Settings] → [Screenshot] and turn on [Enable Screenshot]. If [Screen Recording Permission] appears on macOS, choose [Authorize]; after authorization, click [Restart Now].

2

2. Set the hotkey

The default hotkey is macOS's Command+Shift+Aand Windows and Linux's Ctrl+Shift+A. Click [Set Hotkey] to jump to the corresponding row; if it is already occupied by the system or another app, the page will show a conflict warning.

3

3. Select and annotate

After pressing the hotkey, drag to select a region. Use [Rectangle], [Arrow], [Brush], and [Text] to highlight key points, and use [Mosaic] to cover sensitive information; the property panel lets you adjust color, line width, and font size.

4

4. Copy text or image

When the OCR model is ready, the page will automatically recognize text; you can also click [Recognize Text]. Directly select text or choose [Copy All Text]; after finishing annotations, choose [Copy and Close] or [Save Image].

Expected results

The screenshot contains only the selected area; the annotations are clear and sensitive information has been obscured; after copying, you can paste the image into the target app, or paste the OCR text as editable text.

Key screenshots

快捷键设置中的屏幕截图快捷键
① [Screenshot] is a customizable global hotkey; after changing it, test it once in a non-Cherry Studio window first.

Configuration notes

Configuration item
Product default
Recommended starting point
Function
Applicable scenario
Notes

Enable screenshot

Disable

Turn on when needed

Register global screenshot hotkey

Daily screenshots, tutorials, issue reports

macOS requires Screen Recording permission

Screenshot hotkey

Command/Ctrl+Shift+A

Keep the default unless there is a conflict

Trigger screenshots from any app

High-frequency cross-app use

Will not trigger when it conflicts with other apps

Automatically recognize text

Enable

Keep it on if you often copy text from screenshots

Automatically run OCR after taking a screenshot

Error screenshots, tables, interface text

Need to download a local OCR model

截图设置中的启用开关、快捷键和本地 OCR 状态

User case

A tester captured a configuration error, used a rectangle to frame the error message, used a mosaic to obscure the account and local path, and then copied it into the issue feedback assistant. Later, they copied the error code from the same screenshot and pasted it into the reproduction steps to avoid mistakes from manual entry.

FAQ

What should I do if pressing the hotkey does nothing?

Make sure [Enable Screenshot] is turned on, then check whether a conflict warning appears next to the hotkey. On macOS, also check Screen Recording permission and restart after authorization; on Windows and Linux, try changing to a combination not used by the system.

Why can't I copy text?

Open [Settings] → [Local Models] and make sure the OCR model status is Ready. Text cannot be recognized while annotating; finish or undo the current annotation first, then run OCR.

References

  • Issue feedback and feature requests

  • Input toolbar and productivity tools

Last updated

Was this helpful?