diff --git a/README.md b/README.md
index 0885e17..a0c7059 100644
--- a/README.md
+++ b/README.md
@@ -29,7 +29,8 @@ However:
 - you can switch OCR provider with its corresponding keyboard key (refer to the list above). You can also start the script paused with the -p option or with a specific provider with the -e option (refer to `owocr -h` for the list)
 - holding ctrl or cmd at any time will pause image processing temporarily
 - for systems where text can be copied to the clipboard at the same time as images, if `*ocr_ignore*` is copied with an image, the image will be ignored
-- a config file (located in `user directory/.config/owocr_config.ini`) can be used to limit providers (to reduce clutter/memory usage) as well as specifying provider settings such as api keys etc (a sample config file is provided)
+- optionally, notifications can be enabled in the config file to show the text with a native OS notification
+- a config file (to be created in `user directory/.config/owocr_config.ini`, on Windows `user directory` is the `C:\Users\yourusername` folder) can be used to limit providers (to reduce clutter/memory usage) as well as specifying provider settings such as api keys etc. A sample config file is provided [here](https://raw.githubusercontent.com/AuroraWright/owocr/master/owocr_config.ini)
 
 # Acknowledgments
 
diff --git a/owocr/run.py b/owocr/run.py
index 5e37acd..4e30c84 100644
--- a/owocr/run.py
+++ b/owocr/run.py
@@ -17,6 +17,7 @@ from PIL import Image
 from PIL import UnidentifiedImageError
 from loguru import logger
 from pynput import keyboard
+from desktop_notifier import DesktopNotifier
 
 import inspect
 from owocr import *
@@ -77,12 +78,14 @@ def are_images_identical(img1, img2):
     return (img1.shape == img2.shape) and (img1 == img2).all()
 
 
-def process_and_write_results(engine_instance, engine_color, img_or_path, write_to):
+def process_and_write_results(engine_instance, engine_color, img_or_path, write_to, notifier):
     t0 = time.time()
     text = engine_instance(img_or_path)
     t1 = time.time()
 
     logger.opt(ansi=True).info(f"Text recognized in {t1 - t0:0.03f}s using <{engine_color}>{engine_instance.readable_name}</{engine_color}>: {text}")
+    if notifier != None:
+        notifier.send_sync(title="owocr", message=text, timeout=5)
 
     if write_to == 'websocket':
         websocket_server_thread.send_text(text)
@@ -182,6 +185,7 @@ def run(read_from='clipboard',
     engine_color = 'cyan'
     delay_secs = 0.5
     websocket_port = 7331
+    notifier = None
 
     config_file = os.path.join(os.path.expanduser('~'),'.config','owocr_config.ini')
     config = configparser.ConfigParser()
@@ -214,6 +218,12 @@ def run(read_from='clipboard',
         except KeyError:
             pass
 
+        try:
+            if config['general']['notifications'].strip() == 'True':
+                notifier = DesktopNotifier()
+        except KeyError:
+            pass
+
     logger.configure(handlers=[{"sink": sys.stderr, "format": logger_format}])
 
     if len(res) != 0:
@@ -337,7 +347,7 @@ def run(read_from='clipboard',
                 else:
                     if not paused and not tmp_paused:
                         img = Image.open(io.BytesIO(item))
-                        process_and_write_results(engine_instances[engine_index], engine_color, img, write_to)
+                        process_and_write_results(engine_instances[engine_index], engine_color, img, write_to, notifier)
         elif read_from == 'clipboard':
             if not paused and not tmp_paused:
                 if mac_clipboard_polling:
@@ -363,7 +373,7 @@ def run(read_from='clipboard',
                             logger.warning('Error while reading from clipboard ({})'.format(error))
                     else:
                         if not just_unpaused and (ignore_flag or pyperclip.paste() != '*ocr_ignore*') and isinstance(img, Image.Image) and not are_images_identical(img, old_img):
-                            process_and_write_results(engine_instances[engine_index], engine_color, img, write_to)
+                            process_and_write_results(engine_instances[engine_index], engine_color, img, write_to, notifier)
 
             if just_unpaused:
                 just_unpaused = False
@@ -383,7 +393,7 @@ def run(read_from='clipboard',
                             except (UnidentifiedImageError, OSError) as e:
                                 logger.warning(f'Error while reading file {path}: {e}')
                             else:
-                                process_and_write_results(engine_instances[engine_index], engine_color, img, write_to)
+                                process_and_write_results(engine_instances[engine_index], engine_color, img, write_to, notifier)
                                 img.close()
                                 if delete_images:
                                     Path.unlink(path)
diff --git a/owocr_config.ini b/owocr_config.ini
index 4c1701f..0c596cc 100644
--- a/owocr_config.ini
+++ b/owocr_config.ini
@@ -4,6 +4,7 @@
 ;engine_color = cyan
 ;websocket_port = 7331
 ;delay_secs = 0.5
+;notifications = False
 [winrtocr]
 ;url = http://aaa.xxx.yyy.zzz:8000
 [azure]
diff --git a/requirements.txt b/requirements.txt
index 35d6460..c049f41 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,4 +6,5 @@ Pillow>=10.0.0
 pyperclip
 unidic_lite
 pynput
-websockets
\ No newline at end of file
+websockets
+desktop-notifier
\ No newline at end of file
diff --git a/setup.py b/setup.py
index a12f447..39e140d 100644
--- a/setup.py
+++ b/setup.py
@@ -27,7 +27,8 @@ setup(
         "pyperclip",
         "unidic_lite",
         "pynput",
-        "websockets"
+        "websockets",
+        "desktop-notifier"
     ],
     entry_points={
         "console_scripts": [