h

.gitignore

@@ -27,3 +27,4 @@ wheels/
 /Users/wongdingfeng/.config/tooling/.env
 /Users/wongdingfeng/.config/tooling/.DS_Store
 /Users/wongdingfeng/.config/tooling/Thumbs.db
+uv.lock

pyproject.toml

@@ -13,8 +13,9 @@ dependencies = [
     "python-doctr>=0.8.0",
     "typer>=0.12.0",
     "rich>=13.0.0",
-    "realtimestt>=0.3.104",
     "rumps>=0.4.0",
+    "realtimestt>=0.3.104",
+    "pyautogui>=0.9.54",
 ]
 
 [project.optional-dependencies]

src/tooling/stt_cli.py

@@ -28,6 +28,12 @@ try:
 except ImportError:
     RUMPS_AVAILABLE = False
 
+try:
+    import pyautogui
+    PYAUTOGUI_AVAILABLE = True
+except ImportError:
+    PYAUTOGUI_AVAILABLE = False
+
 # Create STT app that can be imported as a subcommand
 stt_app = typer.Typer(
     name="stt",
@@ -111,7 +117,7 @@ if RUMPS_AVAILABLE:
             self.language = ""
             self.realtime = True
             self.sensitivity = 0.6
-            self.device = "auto"
+            self.device = "mps"
             self.wakeword_backend = "openwakeword"
             self.save_to_file = None
             
@@ -189,14 +195,14 @@ if RUMPS_AVAILABLE:
             self.wake_word = sender.title
             self.set_current_wake_word()
             if self.is_running:
-                rumps.notification("STT Settings", "Wake Word Changed", f"Restart STT to use '{self.wake_word}'")
+                rumps.notification("STT Settings", "Wake Word Changed", f"Restart STT to use '{self.wake_word}'", sound=False)
         
         def set_model(self, sender):
             """Set the model from menu selection."""
             self.model = sender.title
             self.set_current_model()
             if self.is_running:
-                rumps.notification("STT Settings", "Model Changed", f"Restart STT to use '{self.model}' model")
+                rumps.notification("STT Settings", "Model Changed", f"Restart STT to use '{self.model}' model", sound=False)
         
         def start_stt(self, _):
             """Start STT functionality."""
@@ -229,9 +235,9 @@ if RUMPS_AVAILABLE:
                 # Configure recorder
                 recorder_config = {
                     "model": self.model,
-                    "wake_words": self.wake_word,
-                    "wakeword_backend": self.wakeword_backend,
-                    "wake_words_sensitivity": self.sensitivity,
+                    # "wake_words": self.wake_word,
+                    # "wakeword_backend": self.wakeword_backend,
+                    # "wake_words_sensitivity": self.sensitivity,
                     "device": self.device,
                     "on_recording_start": self.on_recording_start,
                     "on_recording_stop": self.on_recording_stop,
@@ -260,7 +266,7 @@ if RUMPS_AVAILABLE:
                 self.transcription_thread.start()
                 
                 self.update_menu_states()
-                rumps.notification("STT Started", f"Wake word: {self.wake_word}", f"Model: {self.model} | Device: {self.device}")
+                rumps.notification("STT Started", f"Wake word: {self.wake_word}", f"Model: {self.model} | Device: {self.device}", sound=False)
                 
             except Exception as e:
                 rumps.alert("STT Error", f"Failed to start STT: {str(e)}")
@@ -288,7 +294,7 @@ if RUMPS_AVAILABLE:
                 self.output_file = None
             
             self.update_menu_states()
-            rumps.notification("STT Stopped", "Speech-to-text has been stopped", "")
+            rumps.notification("STT Stopped", "Speech-to-text has been stopped", "", sound=False)
         
         def pause_stt(self, _):
             """Pause STT functionality."""
@@ -297,7 +303,7 @@ if RUMPS_AVAILABLE:
             
             self.is_paused = True
             self.update_menu_states()
-            rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu")
+            rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu", sound=False)
         
         def resume_stt(self, _):
             """Resume STT functionality."""
@@ -306,7 +312,7 @@ if RUMPS_AVAILABLE:
             
             self.is_paused = False
             self.update_menu_states()
-            rumps.notification("STT Resumed", "Speech recognition resumed", f"Listening for '{self.wake_word}'")
+            rumps.notification("STT Resumed", "Speech recognition resumed", f"Listening for '{self.wake_word}'", sound=False)
         
         def transcription_loop(self):
             """Main transcription loop running in background thread."""
@@ -337,8 +343,8 @@ if RUMPS_AVAILABLE:
             """Handle completed transcriptions."""
             if text.strip():
                 # Show notification with transcription
-                rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else ""))
-                
+                rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else ""), sound=False)
+                pyautogui.typewrite(text + " ")
                 # Save to file if specified
                 if self.output_file:
                     timestamp = datetime.datetime.now().strftime("%H:%M:%S")
@@ -395,7 +401,7 @@ if RUMPS_AVAILABLE:
                 
                 if response.clicked and response.text:
                     self.save_to_file = Path.home() / "Documents" / response.text
-                    rumps.notification("File Set", "Transcriptions will be saved to:", str(self.save_to_file))
+                    rumps.notification("File Set", "Transcriptions will be saved to:", str(self.save_to_file), sound=False)
             except Exception as e:
                 rumps.alert("Error", f"Could not set output file: {e}")
 

test_realtime_stt.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python3
+"""
+Simple RealtimeSTT Test Script
+
+Test wake word detection and transcription functionality
+without the complexity of threading and status bar apps.
+"""
+
+from RealtimeSTT import AudioToTextRecorder
+
+def process_text(text):
+    print(text)
+
+if __name__ == '__main__':
+    print("Wait until it says 'speak now'")
+    recorder = AudioToTextRecorder()
+
+    while True:
+        recorder.text(process_text)

uv.lock

@@ -6257,6 +6257,7 @@ source = { editable = "." }
 dependencies = [
     { name = "pillow", version = "11.1.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.13'" },
     { name = "pillow", version = "11.2.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.13'" },
+    { name = "pyautogui" },
     { name = "pyperclip" },
     { name = "python-doctr" },
     { name = "realtimestt" },
@@ -6292,6 +6293,7 @@ requires-dist = [
     { name = "mss", marker = "extra == 'screenshot-all'", specifier = ">=7.0.0" },
     { name = "mss", marker = "extra == 'screenshot-fast'", specifier = ">=7.0.0" },
     { name = "pillow", specifier = ">=11.1.0" },
+    { name = "pyautogui", specifier = ">=0.9.54" },
     { name = "pyautogui", marker = "extra == 'screenshot-all'", specifier = ">=0.9.54" },
     { name = "pyautogui", marker = "extra == 'screenshot-full'", specifier = ">=0.9.54" },
     { name = "pyperclip", specifier = ">=1.9.0" },