a

.gitignore

@@ -27,3 +27,5 @@ wheels/
 /Users/wongdingfeng/.config/tooling/.env
 /Users/wongdingfeng/.config/tooling/.DS_Store
 /Users/wongdingfeng/.config/tooling/Thumbs.db
+uv.lock
+realtimesst.log

README.md

@@ -288,6 +288,22 @@ The following wake words are supported:
 - porcupine
 - terminator
 
+### Wake Word Engines
+
+Two wake word engines are supported:
+
+- **openwakeword** (default) - Open source, free to use, good accuracy
+- **pvporcupine** - Picovoice's Porcupine engine, highly optimized
+
+Choose the engine based on your requirements:
+```bash
+# Use OpenWakeWord (default)
+tooling stt listen --wakeword-engine openwakeword
+
+# Use Porcupine for better performance
+tooling stt listen --wakeword-engine pvporcupine
+```
+
 ### Available Models
 
 | Model | Speed | Accuracy | Memory | Use Case |
@@ -311,6 +327,7 @@ Options:
   --save-to-file PATH    Save transcriptions to a file
   --sensitivity FLOAT    Wake word sensitivity (0.0 to 1.0) [default: 0.6]
   --device TEXT          Device to use (auto, cuda, cpu) [default: auto]
+  --wakeword-engine TEXT Wake word engine (openwakeword, pvporcupine) [default: openwakeword]
   --verbose              Show verbose output and configuration
   --help                 Show this message and exit
 ```
@@ -342,6 +359,11 @@ tooling stt test --duration 5 --model tiny
 tooling stt listen --language es --sensitivity 0.8 --wake-word "hey google"
 ```
 
+**Use different wake word engine:**
+```bash
+tooling stt listen --wakeword-engine pvporcupine --wake-word alexa
+```
+
 ### How it Works
 
 1. **Initialization**: Loads the selected Whisper model and sets up audio processing

STT_STATUSBAR_USAGE.md

@@ -0,0 +1,116 @@
+# STT Status Bar App Usage
+
+## Overview
+
+The STT (Speech-to-Text) status bar app provides a convenient macOS menu bar interface for controlling speech-to-text functionality using wake word activation.
+
+## Features
+
+- **Start/Stop/Pause/Resume**: Full control over STT recording
+- **Status Indicators**: Visual status in menu bar (🎙️🔴 recording, 🎙️⏸️ paused, 🎙️⚫ stopped)
+- **Configurable Settings**: Change wake words and models on the fly
+- **File Output**: Save transcriptions to a file
+- **Notifications**: Real-time notifications for transcriptions and status changes
+
+## Usage
+
+### Starting the Status Bar App
+
+```bash
+# Launch the status bar app
+tooling stt statusbar
+
+# Or using the full CLI path
+python -m tooling.cli stt statusbar
+```
+
+### Menu Options
+
+#### Main Controls
+- **Start STT**: Begin speech-to-text with current settings
+- **Stop STT**: Stop speech-to-text completely  
+- **Pause**: Temporarily pause recognition (keeps recorder alive)
+- **Resume**: Resume recognition from pause
+
+#### Settings
+- **Wake Word**: Choose from predefined options:
+  - jarvis (default)
+  - alexa
+  - hey google
+  - hey siri
+  - computer
+  
+- **Model**: Select Whisper model:
+  - tiny (fastest, least accurate)
+  - base (default, good balance)
+  - small (more accurate)
+  - medium (most accurate, slower)
+
+#### File Management
+- **Show Recent Transcriptions**: Display last 10 transcription entries
+- **Save to File...**: Set output file for saving transcriptions
+
+### Status Indicators
+
+| Icon | Status | Description |
+|------|--------|-------------|
+| 🎙️⚫ | Stopped | STT is not running |
+| 🎙️🔴 | Recording | STT is active and listening |
+| 🎙️⏸️ | Paused | STT is paused but can be resumed |
+
+### Workflow Example
+
+1. **Launch the app**: `tooling stt statusbar`
+2. **Look for the 🎙️ icon** in your macOS menu bar
+3. **Click the icon** to open the menu
+4. **Set your preferences**:
+   - Choose wake word from Settings > Wake Word
+   - Select model from Settings > Model
+   - Optionally set output file with "Save to File..."
+5. **Click "Start STT"** to begin
+6. **Say your wake word** (e.g., "jarvis") to trigger recording
+7. **Speak clearly** after the wake word is detected
+8. **Get notifications** with your transcribed text
+9. **Use Pause/Resume** as needed
+10. **Click "Stop STT"** when done
+
+### Notifications
+
+The app provides notifications for:
+- STT started/stopped/paused/resumed
+- Transcribed speech (shows first 100 characters)
+- Settings changes (when STT is running)
+- File operations
+
+### File Output
+
+When you set an output file:
+- Transcriptions are saved with timestamps
+- Sessions are marked with start/end timestamps
+- File is automatically created in ~/Documents/ by default
+- Each transcription includes: `[HH:MM:SS] transcribed text`
+
+### Requirements
+
+- macOS (rumps requires macOS and PyObjC)
+- RealtimeSTT library
+- Working microphone
+- Python 3.11+
+
+### Troubleshooting
+
+- **No menu bar icon**: Make sure you're running on macOS and rumps is installed
+- **No transcriptions**: Check microphone permissions and try speaking louder
+- **Wake word not detected**: Try adjusting sensitivity or use a different wake word
+- **High CPU usage**: Consider using the "tiny" model for better performance
+
+### Advanced Configuration
+
+The status bar app uses sensible defaults, but you can modify the underlying configuration by editing the STTStatusBarApp class in `src/tooling/stt_cli.py`.
+
+Default settings:
+- Wake word: "jarvis"
+- Model: "base"
+- Sensitivity: 0.6
+- Device: auto-detect (CUDA if available, otherwise CPU)
+- Realtime display: enabled 

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",
+    "pynput>=1.7.6",
+    "realtimestt",
 ]
 
 [project.optional-dependencies]
@@ -28,6 +29,9 @@ screenshot-all = [
     "pyscreenshot>=3.1"
 ]  # All screenshot libraries for maximum compatibility
 
+# Keyboard automation
+keyboard = ["pynput>=1.7.6"]  # Cross-platform keyboard automation
+
 [project.scripts]
 ocr-screenshot = "tooling.cli:cli_main"
 tooling = "tooling.cli:cli_main"
@@ -40,3 +44,6 @@ build-backend = "hatchling.build"
 dev = [
     "open-webui>=0.6.5",
 ]
+
+[tool.uv.sources]
+realtimestt = { path = "../../projects/RealtimeSTT" }

src/tooling/stt_cli.py

@@ -28,6 +28,12 @@ try:
 except ImportError:
     RUMPS_AVAILABLE = False
 
+try:
+    from pynput.keyboard import Controller as KeyboardController
+    PYNPUT_AVAILABLE = True
+except ImportError:
+    PYNPUT_AVAILABLE = False
+
 # Create STT app that can be imported as a subcommand
 stt_app = typer.Typer(
     name="stt",
@@ -96,300 +102,315 @@ if RUMPS_AVAILABLE:
         
         def __init__(self, name="STT", **kwargs):
             super().__init__(name, **kwargs)
-        
-        # Initialize state
-        self.recorder = None
-        self.is_running = False
-        self.is_paused = False
-        self.output_file = None
-        self.transcription_thread = None
-        self.stop_event = threading.Event()
-        
-        # Configuration
-        self.wake_word = "jarvis"
-        self.model = "base"
-        self.language = ""
-        self.realtime = True
-        self.sensitivity = 0.6
-        self.device = "auto"
-        self.save_to_file = None
-        
-        # Menu setup
-        self.menu = [
-            rumps.MenuItem("Start STT", callback=self.start_stt),
-            rumps.MenuItem("Stop STT", callback=self.stop_stt),
-            rumps.separator,
-            rumps.MenuItem("Pause", callback=self.pause_stt),
-            rumps.MenuItem("Resume", callback=self.resume_stt),
-            rumps.separator,
-            {
-                "Settings": {
-                    "Wake Word": {
-                        "jarvis": rumps.MenuItem("jarvis", callback=self.set_wake_word),
-                        "alexa": rumps.MenuItem("alexa", callback=self.set_wake_word),
-                        "hey google": rumps.MenuItem("hey google", callback=self.set_wake_word),
-                        "hey siri": rumps.MenuItem("hey siri", callback=self.set_wake_word),
-                        "computer": rumps.MenuItem("computer", callback=self.set_wake_word),
-                    },
-                    "Model": {
-                        "tiny": rumps.MenuItem("tiny", callback=self.set_model),
-                        "base": rumps.MenuItem("base", callback=self.set_model),
-                        "small": rumps.MenuItem("small", callback=self.set_model),
-                        "medium": rumps.MenuItem("medium", callback=self.set_model),
-                    }
-                }
-            },
-            rumps.separator,
-            rumps.MenuItem("Show Recent Transcriptions", callback=self.show_transcriptions),
-            rumps.MenuItem("Save to File...", callback=self.select_output_file),
-            rumps.separator,
-            rumps.MenuItem("Quit", callback=rumps.quit_application),
-        ]
-        
-        # Set initial menu states
-        self.update_menu_states()
-        self.set_current_wake_word()
-        self.set_current_model()
-    
-    def update_menu_states(self):
-        """Update menu item states based on current status."""
-        if self.is_running:
-            if self.is_paused:
-                self.title = "🎙️⏸️"
-                self.menu["Start STT"].set_callback(None)
-                self.menu["Stop STT"].set_callback(self.stop_stt)
-                self.menu["Pause"].set_callback(None)
-                self.menu["Resume"].set_callback(self.resume_stt)
-            else:
-                self.title = "🎙️🔴"
-                self.menu["Start STT"].set_callback(None)
-                self.menu["Stop STT"].set_callback(self.stop_stt)
-                self.menu["Pause"].set_callback(self.pause_stt)
-                self.menu["Resume"].set_callback(None)
-        else:
-            self.title = "🎙️⚫"
-            self.menu["Start STT"].set_callback(self.start_stt)
-            self.menu["Stop STT"].set_callback(None)
-            self.menu["Pause"].set_callback(None)
-            self.menu["Resume"].set_callback(None)
-    
-    def set_current_wake_word(self):
-        """Set checkmark for current wake word."""
-        for word in ["jarvis", "alexa", "hey google", "hey siri", "computer"]:
-            self.menu["Settings"]["Wake Word"][word].state = (word == self.wake_word)
-    
-    def set_current_model(self):
-        """Set checkmark for current model."""
-        for model in ["tiny", "base", "small", "medium"]:
-            self.menu["Settings"]["Model"][model].state = (model == self.model)
-    
-    def set_wake_word(self, sender):
-        """Set the wake word from menu selection."""
-        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}'")
-    
-    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")
-    
-    def start_stt(self, _):
-        """Start STT functionality."""
-        if self.is_running:
-            return
-        
-        try:
-            from RealtimeSTT import AudioToTextRecorder
-        except ImportError:
-            rumps.alert("RealtimeSTT not installed", "Please install with: pip install RealtimeSTT")
-            return
-        
-        try:
-            # Determine device
-            if self.device == "auto":
-                try:
-                    import torch
-                    self.device = "cuda" if torch.cuda.is_available() else "cpu"
-                except ImportError:
-                    self.device = "cpu"
             
-            # Setup output file if specified
-            if self.save_to_file:
-                self.save_to_file.parent.mkdir(parents=True, exist_ok=True)
-                self.output_file = open(self.save_to_file, 'a', encoding='utf-8')
-                timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-                self.output_file.write(f"\n=== STT Session Started: {timestamp} ===\n")
-                self.output_file.flush()
-            
-            # Configure recorder
-            recorder_config = {
-                "model": self.model,
-                "wake_words": self.wake_word,
-                "wake_words_sensitivity": self.sensitivity,
-                "device": self.device,
-                "on_recording_start": self.on_recording_start,
-                "on_recording_stop": self.on_recording_stop,
-                "on_wakeword_detected": self.on_wakeword_detected,
-                "on_wakeword_timeout": self.on_wakeword_timeout,
-                "on_wakeword_detection_start": self.on_wakeword_detection_start,
-            }
-            
-            if self.language:
-                recorder_config["language"] = self.language
-            
-            if self.realtime:
-                recorder_config.update({
-                    "enable_realtime_transcription": True,
-                    "on_realtime_transcription_update": self.on_realtime_transcription,
-                })
-            
-            # Initialize recorder
-            self.recorder = AudioToTextRecorder(**recorder_config)
-            
-            # Start transcription thread
-            self.is_running = True
+            # Initialize state
+            self.recorder = None
+            self.is_running = False
             self.is_paused = False
-            self.stop_event.clear()
-            self.transcription_thread = threading.Thread(target=self.transcription_loop, daemon=True)
-            self.transcription_thread.start()
+            self.output_file = None
+            self.transcription_thread = None
+            self.stop_event = threading.Event()
+            
+            # Configuration
+            self.wake_word = "jarvis"
+            self.model = "base"
+            self.language = ""
+            self.realtime = True
+            self.sensitivity = 0.6
+            self.device = "auto"
+            self.wakeword_backend = "openwakeword"
+            self.save_to_file = None
+            
+            # Menu setup
+            self.menu = [
+                rumps.MenuItem("Start STT", callback=self.start_stt),
+                rumps.MenuItem("Stop STT", callback=self.stop_stt),
+                rumps.separator,
+                rumps.MenuItem("Pause", callback=self.pause_stt),
+                rumps.MenuItem("Resume", callback=self.resume_stt),
+                rumps.separator,
+                {
+                    "Settings": {
+                        "Wake Word": {
+                            "jarvis": rumps.MenuItem("jarvis", callback=self.set_wake_word),
+                            "alexa": rumps.MenuItem("alexa", callback=self.set_wake_word),
+                            "hey google": rumps.MenuItem("hey google", callback=self.set_wake_word),
+                            "hey siri": rumps.MenuItem("hey siri", callback=self.set_wake_word),
+                            "computer": rumps.MenuItem("computer", callback=self.set_wake_word),
+                        },
+                        "Model": {
+                            "tiny": rumps.MenuItem("tiny", callback=self.set_model),
+                            "base": rumps.MenuItem("base", callback=self.set_model),
+                            "small": rumps.MenuItem("small", callback=self.set_model),
+                            "medium": rumps.MenuItem("medium", callback=self.set_model),
+                        }
+                    }
+                },
+                rumps.separator,
+                rumps.MenuItem("Show Recent Transcriptions", callback=self.show_transcriptions),
+                rumps.MenuItem("Save to File...", callback=self.select_output_file),
+                rumps.separator,
+                rumps.MenuItem("Quit", callback=rumps.quit_application),
+            ]
+            
+            # Set initial menu states
+            self.update_menu_states()
+            self.set_current_wake_word()
+            self.set_current_model()
+        
+        def update_menu_states(self):
+            """Update menu item states based on current status."""
+            if self.is_running:
+                if self.is_paused:
+                    self.title = "🎙️⏸️"
+                    self.menu["Start STT"].set_callback(None)
+                    self.menu["Stop STT"].set_callback(self.stop_stt)
+                    self.menu["Pause"].set_callback(None)
+                    self.menu["Resume"].set_callback(self.resume_stt)
+                else:
+                    self.title = "🎙️🔴"
+                    self.menu["Start STT"].set_callback(None)
+                    self.menu["Stop STT"].set_callback(self.stop_stt)
+                    self.menu["Pause"].set_callback(self.pause_stt)
+                    self.menu["Resume"].set_callback(None)
+            else:
+                self.title = "🎙️⚫"
+                self.menu["Start STT"].set_callback(self.start_stt)
+                self.menu["Stop STT"].set_callback(None)
+                self.menu["Pause"].set_callback(None)
+                self.menu["Resume"].set_callback(None)
+        
+        def set_current_wake_word(self):
+            """Set checkmark for current wake word."""
+            for word in ["jarvis", "alexa", "hey google", "hey siri", "computer"]:
+                self.menu["Settings"]["Wake Word"][word].state = (word == self.wake_word)
+        
+        def set_current_model(self):
+            """Set checkmark for current model."""
+            for model in ["tiny", "base", "small", "medium"]:
+                self.menu["Settings"]["Model"][model].state = (model == self.model)
+        
+        def set_wake_word(self, sender):
+            """Set the wake word from menu selection."""
+            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}'", 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", sound=False)
+        
+        def start_stt(self, _):
+            """Start STT functionality."""
+            if self.is_running:
+                return
+            
+            try:
+                from RealtimeSTT import AudioToTextRecorder
+            except ImportError:
+                rumps.alert("RealtimeSTT not installed", "Please install with: pip install RealtimeSTT")
+                return
+            
+            try:
+                # Determine device
+                if self.device == "auto":
+                    try:
+                        import torch
+                        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+                    except ImportError:
+                        self.device = "cpu"
+                
+                # Setup output file if specified
+                if self.save_to_file:
+                    self.save_to_file.parent.mkdir(parents=True, exist_ok=True)
+                    self.output_file = open(self.save_to_file, 'a', encoding='utf-8')
+                    timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+                    self.output_file.write(f"\n=== STT Session Started: {timestamp} ===\n")
+                    self.output_file.flush()
+                
+                # Configure recorder
+                recorder_config = {
+                    "model": self.model,
+                    # "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,
+                    "on_wakeword_detected": self.on_wakeword_detected,
+                    "on_wakeword_timeout": self.on_wakeword_timeout,
+                    "on_wakeword_detection_start": self.on_wakeword_detection_start,
+                }
+                
+                if self.language:
+                    recorder_config["language"] = self.language
+                
+                if self.realtime:
+                    recorder_config.update({
+                        "enable_realtime_transcription": True,
+                        "on_realtime_transcription_update": self.on_realtime_transcription,
+                    })
+                
+                # Initialize recorder
+                self.recorder = AudioToTextRecorder(**recorder_config)
+                
+                # Start transcription thread
+                self.is_running = True
+                self.is_paused = False
+                self.stop_event.clear()
+                self.transcription_thread = threading.Thread(target=self.transcription_loop, daemon=True)
+                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}", sound=False)
+                
+            except Exception as e:
+                rumps.alert("STT Error", f"Failed to start STT: {str(e)}")
+        
+        def stop_stt(self, _):
+            """Stop STT functionality."""
+            if not self.is_running:
+                return
+            
+            self.is_running = False
+            self.is_paused = False
+            self.stop_event.set()
+            
+            if self.recorder:
+                try:
+                    self.recorder.shutdown()
+                except:
+                    pass
+                self.recorder = None
+            
+            if self.output_file:
+                timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+                self.output_file.write(f"=== STT Session Ended: {timestamp} ===\n\n")
+                self.output_file.close()
+                self.output_file = None
             
             self.update_menu_states()
-            rumps.notification("STT Started", f"Wake word: {self.wake_word}", f"Model: {self.model} | Device: {self.device}")
+            rumps.notification("STT Stopped", "Speech-to-text has been stopped", "", sound=False)
+        
+        def pause_stt(self, _):
+            """Pause STT functionality."""
+            if not self.is_running or self.is_paused:
+                return
             
-        except Exception as e:
-            rumps.alert("STT Error", f"Failed to start STT: {str(e)}")
-    
-    def stop_stt(self, _):
-        """Stop STT functionality."""
-        if not self.is_running:
-            return
+            self.is_paused = True
+            self.update_menu_states()
+            rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu", sound=False)
         
-        self.is_running = False
-        self.is_paused = False
-        self.stop_event.set()
-        
-        if self.recorder:
-            try:
-                self.recorder.shutdown()
-            except:
-                pass
-            self.recorder = None
-        
-        if self.output_file:
-            timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-            self.output_file.write(f"=== STT Session Ended: {timestamp} ===\n\n")
-            self.output_file.close()
-            self.output_file = None
-        
-        self.update_menu_states()
-        rumps.notification("STT Stopped", "Speech-to-text has been stopped", "")
-    
-    def pause_stt(self, _):
-        """Pause STT functionality."""
-        if not self.is_running or self.is_paused:
-            return
-        
-        self.is_paused = True
-        self.update_menu_states()
-        rumps.notification("STT Paused", "Speech recognition paused", "Resume from menu")
-    
-    def resume_stt(self, _):
-        """Resume STT functionality."""
-        if not self.is_running or not self.is_paused:
-            return
-        
-        self.is_paused = False
-        self.update_menu_states()
-        rumps.notification("STT Resumed", "Speech recognition resumed", f"Listening for '{self.wake_word}'")
-    
-    def transcription_loop(self):
-        """Main transcription loop running in background thread."""
-        while self.is_running and not self.stop_event.is_set():
-            try:
-                if not self.is_paused and self.recorder:
-                    text = self.recorder.text()
-                    if text and text.strip():
-                        self.on_transcription_complete(text)
-                else:
-                    time.sleep(0.1)  # Small delay when paused
-            except Exception as e:
-                print(f"Transcription error: {e}")
-                time.sleep(1)  # Longer delay on error
-    
-    def on_realtime_transcription(self, text: str):
-        """Handle real-time transcription updates."""
-        # Could update a notification or log
-        pass
-    
-    def on_transcription_complete(self, text: str):
-        """Handle completed transcriptions."""
-        if text.strip():
-            # Show notification with transcription
-            rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else ""))
+        def resume_stt(self, _):
+            """Resume STT functionality."""
+            if not self.is_running or not self.is_paused:
+                return
             
-            # Save to file if specified
-            if self.output_file:
-                timestamp = datetime.datetime.now().strftime("%H:%M:%S")
-                self.output_file.write(f"[{timestamp}] {text}\n")
-                self.output_file.flush()
-    
-    def on_recording_start(self):
-        """Called when recording starts."""
-        pass
-    
-    def on_recording_stop(self):
-        """Called when recording stops."""
-        pass
-    
-    def on_wakeword_detected(self):
-        """Called when wake word is detected."""
-        pass
-    
-    def on_wakeword_timeout(self):
-        """Called when wake word times out."""
-        pass
-    
-    def on_wakeword_detection_start(self):
-        """Called when starting to listen for wake words."""
-        pass
-    
-    def show_transcriptions(self, _):
-        """Show recent transcriptions in an alert."""
-        if self.output_file and self.save_to_file and self.save_to_file.exists():
-            try:
-                with open(self.save_to_file, 'r', encoding='utf-8') as f:
-                    lines = f.readlines()
-                    recent = ''.join(lines[-10:])  # Last 10 lines
-                    if recent.strip():
-                        rumps.alert("Recent Transcriptions", recent)
+            self.is_paused = False
+            self.update_menu_states()
+            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."""
+            print("test1")
+            while self.is_running and not self.stop_event.is_set():
+                print("test2")
+                try:
+                    if not self.is_paused and self.recorder:
+                        print("test3")
+                        text = self.recorder.text()
+                        print("test4")
+                        if text and text.strip():
+                            print("test5")
+                            self.on_transcription_complete(text)
                     else:
-                        rumps.alert("No Transcriptions", "No transcriptions found yet.")
+                        time.sleep(0.1)  # Small delay when paused
+                except Exception as e:
+                    print(f"Transcription error: {e}")
+                    time.sleep(1)  # Longer delay on error
+            print("test")
+        
+        def on_realtime_transcription(self, text: str):
+            """Handle real-time transcription updates."""
+            # Could update a notification or log
+            pass
+        
+        def on_transcription_complete(self, text: str):
+            """Handle completed transcriptions."""
+            if text.strip():
+                # Show notification with transcription
+                rumps.notification("Transcription", "Speech detected:", text[:100] + ("..." if len(text) > 100 else ""), sound=False)
+                
+                # Type the transcribed text using pynput
+                if PYNPUT_AVAILABLE:
+                    keyboard = KeyboardController()
+                    keyboard.type(text + " ")
+                else:
+                    print(f"pynput not available. Transcription: {text}")
+                
+                # Save to file if specified
+                if self.output_file:
+                    timestamp = datetime.datetime.now().strftime("%H:%M:%S")
+                    self.output_file.write(f"[{timestamp}] {text}\n")
+                    self.output_file.flush()
+        
+        def on_recording_start(self):
+            """Called when recording starts."""
+            pass
+        
+        def on_recording_stop(self):
+            """Called when recording stops."""
+            pass
+        
+        def on_wakeword_detected(self):
+            """Called when wake word is detected."""
+            pass
+        
+        def on_wakeword_timeout(self):
+            """Called when wake word times out."""
+            pass
+        
+        def on_wakeword_detection_start(self):
+            """Called when starting to listen for wake words."""
+            pass
+        
+        def show_transcriptions(self, _):
+            """Show recent transcriptions in an alert."""
+            if self.output_file and self.save_to_file and self.save_to_file.exists():
+                try:
+                    with open(self.save_to_file, 'r', encoding='utf-8') as f:
+                        lines = f.readlines()
+                        recent = ''.join(lines[-10:])  # Last 10 lines
+                        if recent.strip():
+                            rumps.alert("Recent Transcriptions", recent)
+                        else:
+                            rumps.alert("No Transcriptions", "No transcriptions found yet.")
+                except Exception as e:
+                    rumps.alert("Error", f"Could not read transcriptions: {e}")
+            else:
+                rumps.alert("No File", "No output file configured. Use 'Save to File...' to set one.")
+        
+        def select_output_file(self, _):
+            """Select output file for saving transcriptions."""
+            try:
+                # Simple file selection using input dialog
+                response = rumps.Window(
+                    message="Enter filename for transcriptions:",
+                    title="Save Transcriptions",
+                    default_text="stt_transcriptions.txt",
+                    ok="Save",
+                    cancel="Cancel"
+                ).run()
+                
+                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), sound=False)
             except Exception as e:
-                rumps.alert("Error", f"Could not read transcriptions: {e}")
-        else:
-            rumps.alert("No File", "No output file configured. Use 'Save to File...' to set one.")
-    
-    def select_output_file(self, _):
-        """Select output file for saving transcriptions."""
-        try:
-            # Simple file selection using input dialog
-            response = rumps.Window(
-                message="Enter filename for transcriptions:",
-                title="Save Transcriptions",
-                default_text="stt_transcriptions.txt",
-                ok="Save",
-                cancel="Cancel"
-            ).run()
-            
-            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))
-        except Exception as e:
-            rumps.alert("Error", f"Could not set output file: {e}")
+                rumps.alert("Error", f"Could not set output file: {e}")
 
 
 @stt_app.command("listen")
@@ -422,6 +443,10 @@ def listen_cmd(
         default="auto",
         help="Device to use (auto, cuda, cpu)"
     ),
+    wakeword_backend: str = typer.Option(
+        default="openwakeword",
+        help="Wake word backend to use (pvporcupine, openwakeword)"
+    ),
     verbose: bool = typer.Option(
         default=False,
         help="Show verbose output and configuration"
@@ -448,6 +473,13 @@ def listen_cmd(
         console.print(f"Valid options: {', '.join(valid_wake_words)}")
         raise typer.Exit(1)
     
+    # Validate wakeword backend
+    valid_backends = ["pvporcupine", "openwakeword"]
+    if wakeword_backend.lower() not in valid_backends:
+        console.print(f"[bold red]❌ Invalid wakeword backend: {wakeword_backend}[/bold red]")
+        console.print(f"Valid options: {', '.join(valid_backends)}")
+        raise typer.Exit(1)
+    
     # Determine device
     if device == "auto":
         try:
@@ -475,6 +507,7 @@ def listen_cmd(
         config_table.add_column("Value", style="green")
         
         config_table.add_row("Wake Word", wake_word)
+        config_table.add_row("Wakeword Backend", wakeword_backend)
         config_table.add_row("Model", model)
         config_table.add_row("Language", language if language else "Auto-detect")
         config_table.add_row("Device", device)
@@ -530,6 +563,7 @@ def listen_cmd(
         recorder_config = {
             "model": model,
             "wake_words": wake_word,
+            "wakeword_backend": wakeword_backend,
             "wake_words_sensitivity": sensitivity,
             "device": device,
             "on_recording_start": on_recording_start,
@@ -734,12 +768,18 @@ def info_cmd():
     console.print(f"\n[bold cyan]Available Models:[/bold cyan]")
     console.print(", ".join(models))
     
+    # Available wakeword backends
+    backends = ["pvporcupine", "openwakeword"]
+    console.print(f"\n[bold cyan]Available Wakeword Backends:[/bold cyan]")
+    console.print(", ".join(backends))
+    
     # Usage examples
     console.print(f"\n[bold cyan]Usage Examples:[/bold cyan]")
     examples = [
         "tooling stt listen                    # Use jarvis wake word with base model",
         "tooling stt listen --wake-word alexa  # Use alexa wake word",
         "tooling stt listen --model tiny       # Use faster tiny model",
+        "tooling stt listen --wakeword-engine pvporcupine  # Use pvporcupine engine",
         "tooling stt test --duration 5         # Test for 5 seconds",
         "tooling stt listen --save-to-file transcripts.txt  # Save to file",
         "tooling stt statusbar                 # Launch status bar app"

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

@@ -1320,6 +1320,12 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ce/31/55cd413eaccd39125368be33c46de24a1f639f2e12349b0361b4678f3915/eval_type_backport-0.2.2-py3-none-any.whl", hash = "sha256:cb6ad7c393517f476f96d456d0412ea80f0a8cf96f6892834cd9340149111b0a", size = 5830, upload-time = "2024-12-21T20:09:44.175Z" },
 ]
 
+[[package]]
+name = "evdev"
+version = "1.9.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/63/fe/a17c106a1f4061ce83f04d14bcedcfb2c38c7793ea56bfb906a6fadae8cb/evdev-1.9.2.tar.gz", hash = "sha256:5d3278892ce1f92a74d6bf888cc8525d9f68af85dbe336c95d1c87fb8f423069", size = 33301, upload-time = "2025-05-01T19:53:47.69Z" }
+
 [[package]]
 name = "events"
 version = "0.5"
@@ -4896,6 +4902,22 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/0c/94/e4181a1f6286f545507528c78016e00065ea913276888db2262507693ce5/PyMySQL-1.1.1-py3-none-any.whl", hash = "sha256:4de15da4c61dc132f4fb9ab763063e693d521a80fd0e87943b9a453dd4c19d6c", size = 44972, upload-time = "2024-05-21T11:03:41.216Z" },
 ]
 
+[[package]]
+name = "pynput"
+version = "1.8.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "evdev", marker = "'linux' in sys_platform" },
+    { name = "pyobjc-framework-applicationservices", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-quartz", marker = "sys_platform == 'darwin'" },
+    { name = "python-xlib", marker = "'linux' in sys_platform" },
+    { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f0/c3/dccf44c68225046df5324db0cc7d563a560635355b3e5f1d249468268a6f/pynput-1.8.1.tar.gz", hash = "sha256:70d7c8373ee98911004a7c938742242840a5628c004573d84ba849d4601df81e", size = 82289, upload-time = "2025-03-17T17:12:01.481Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/59/4f/ac3fa906ae8a375a536b12794128c5efacade9eaa917a35dfd27ce0c7400/pynput-1.8.1-py2.py3-none-any.whl", hash = "sha256:42dfcf27404459ca16ca889c8fb8ffe42a9fe54f722fd1a3e130728e59e768d2", size = 91693, upload-time = "2025-03-17T17:12:00.094Z" },
+]
+
 [[package]]
 name = "pyobjc-core"
 version = "11.1"
@@ -4910,6 +4932,26 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/49/0f/f5ab2b0e57430a3bec9a62b6153c0e79c05a30d77b564efdb9f9446eeac5/pyobjc_core-11.1-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:f2455683e807f8541f0d83fbba0f5d9a46128ab0d5cc83ea208f0bec759b7f96", size = 708807, upload-time = "2025-06-14T20:44:54.851Z" },
 ]
 
+[[package]]
+name = "pyobjc-framework-applicationservices"
+version = "11.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyobjc-core", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-cocoa", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-coretext", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-quartz", marker = "sys_platform == 'darwin'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/be/3f/b33ce0cecc3a42f6c289dcbf9ff698b0d9e85f5796db2e9cb5dadccffbb9/pyobjc_framework_applicationservices-11.1.tar.gz", hash = "sha256:03fcd8c0c600db98fa8b85eb7b3bc31491701720c795e3f762b54e865138bbaf", size = 224842, upload-time = "2025-06-14T20:56:40.648Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/39/2d/9fde6de0b2a95fbb3d77ba11b3cc4f289dd208f38cb3a28389add87c0f44/pyobjc_framework_applicationservices-11.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:cf45d15eddae36dec2330a9992fc852476b61c8f529874b9ec2805c768a75482", size = 30991, upload-time = "2025-06-14T20:45:18.169Z" },
+    { url = "https://files.pythonhosted.org/packages/38/ec/46a5c710e2d7edf55105223c34fed5a7b7cc7aba7d00a3a7b0405d6a2d1a/pyobjc_framework_applicationservices-11.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:f4a85ccd78bab84f7f05ac65ff9be117839dfc09d48c39edd65c617ed73eb01c", size = 31056, upload-time = "2025-06-14T20:45:18.925Z" },
+    { url = "https://files.pythonhosted.org/packages/c4/06/c2a309e6f37bfa73a2a581d3301321b2033e25b249e2a01e417a3c34e799/pyobjc_framework_applicationservices-11.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:385a89f4d0838c97a331e247519d9e9745aa3f7427169d18570e3c664076a63c", size = 31072, upload-time = "2025-06-14T20:45:19.707Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/5f/357bf498c27f1b4d48385860d8374b2569adc1522aabe32befd77089c070/pyobjc_framework_applicationservices-11.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:f480fab20f3005e559c9d06c9a3874a1f1c60dde52c6d28a53ab59b45e79d55f", size = 31335, upload-time = "2025-06-14T20:45:20.462Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/b6/797fdd81399fe8251196f29a621ba3f3f04d5c579d95fd304489f5558202/pyobjc_framework_applicationservices-11.1-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:e8dee91c6a14fd042f98819dc0ac4a182e0e816282565534032f0e544bfab143", size = 31196, upload-time = "2025-06-14T20:45:21.555Z" },
+    { url = "https://files.pythonhosted.org/packages/68/45/47eba8d7cdf16d778240ed13fb405e8d712464170ed29d0463363a695194/pyobjc_framework_applicationservices-11.1-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:a0ce40a57a9b993793b6f72c4fd93f80618ef54a69d76a1da97b8360a2f3ffc5", size = 31446, upload-time = "2025-06-14T20:45:22.313Z" },
+]
+
 [[package]]
 name = "pyobjc-framework-cocoa"
 version = "11.1"
@@ -4927,6 +4969,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c1/7c/54afe9ffee547c41e1161691e72067a37ed27466ac71c089bfdcd07ca70d/pyobjc_framework_cocoa-11.1-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:1b5de4e1757bb65689d6dc1f8d8717de9ec8587eb0c4831c134f13aba29f9b71", size = 396742, upload-time = "2025-06-14T20:46:57.64Z" },
 ]
 
+[[package]]
+name = "pyobjc-framework-coretext"
+version = "11.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyobjc-core", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-cocoa", marker = "sys_platform == 'darwin'" },
+    { name = "pyobjc-framework-quartz", marker = "sys_platform == 'darwin'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/65/e9/d3231c4f87d07b8525401fd6ad3c56607c9e512c5490f0a7a6abb13acab6/pyobjc_framework_coretext-11.1.tar.gz", hash = "sha256:a29bbd5d85c77f46a8ee81d381b847244c88a3a5a96ac22f509027ceceaffaf6", size = 274702, upload-time = "2025-06-14T20:57:16.059Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4c/59/d6cc5470157cfd328b2d1ee2c1b6f846a5205307fce17291b57236d9f46e/pyobjc_framework_coretext-11.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:b4f4d2d2a6331fa64465247358d7aafce98e4fb654b99301a490627a073d021e", size = 30072, upload-time = "2025-06-14T20:48:34.248Z" },
+    { url = "https://files.pythonhosted.org/packages/32/67/9cc5189c366e67dc3e5b5976fac73cc6405841095f795d3fa0d5fc43d76a/pyobjc_framework_coretext-11.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:1597bf7234270ee1b9963bf112e9061050d5fb8e1384b3f50c11bde2fe2b1570", size = 30175, upload-time = "2025-06-14T20:48:35.023Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/d1/6ec2ef4f8133177203a742d5db4db90bbb3ae100aec8d17f667208da84c9/pyobjc_framework_coretext-11.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:37e051e8f12a0f47a81b8efc8c902156eb5bc3d8123c43e5bd4cebd24c222228", size = 30180, upload-time = "2025-06-14T20:48:35.766Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/84/d4a95e49f6af59503ba257fbed0471b6932f0afe8b3725c018dd3ba40150/pyobjc_framework_coretext-11.1-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:56a3a02202e0d50be3c43e781c00f9f1859ab9b73a8342ff56260b908e911e37", size = 30768, upload-time = "2025-06-14T20:48:36.869Z" },
+    { url = "https://files.pythonhosted.org/packages/64/4c/16e1504e06a5cb23eec6276835ddddb087637beba66cf84b5c587eba99be/pyobjc_framework_coretext-11.1-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:15650ba99692d00953e91e53118c11636056a22c90d472020f7ba31500577bf5", size = 30155, upload-time = "2025-06-14T20:48:37.948Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/a4/cbfa9c874b2770fb1ba5c38c42b0e12a8b5aa177a5a86d0ad49b935aa626/pyobjc_framework_coretext-11.1-cp314-cp314t-macosx_11_0_universal2.whl", hash = "sha256:fb27f66a56660c31bb956191d64b85b95bac99cfb833f6e99622ca0ac4b3ba12", size = 30768, upload-time = "2025-06-14T20:48:38.734Z" },
+]
+
 [[package]]
 name = "pyobjc-framework-quartz"
 version = "11.1"
@@ -5258,6 +5319,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3c/32/b4fb8585d1be0f68bde7e110dffbcf354915f77ad8c778563f0ad9655c02/python_socketio-5.13.0-py3-none-any.whl", hash = "sha256:51f68d6499f2df8524668c24bcec13ba1414117cfb3a90115c559b601ab10caf", size = 77800, upload-time = "2025-04-12T15:46:58.412Z" },
 ]
 
+[[package]]
+name = "python-xlib"
+version = "0.33"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "six" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/86/f5/8c0653e5bb54e0cbdfe27bf32d41f27bc4e12faa8742778c17f2a71be2c0/python-xlib-0.33.tar.gz", hash = "sha256:55af7906a2c75ce6cb280a584776080602444f75815a7aff4d287bb2d7018b32", size = 269068, upload-time = "2022-12-25T18:53:00.824Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fc/b8/ff33610932e0ee81ae7f1269c890f697d56ff74b9f5b2ee5d9b7fa2c5355/python_xlib-0.33-py2.py3-none-any.whl", hash = "sha256:c3534038d42e0df2f1392a1b30a15a4ff5fdc2b86cfa94f072bf11b10a164398", size = 182185, upload-time = "2022-12-25T18:52:58.662Z" },
+]
+
 [[package]]
 name = "python3-xlib"
 version = "0.15"
@@ -5493,7 +5566,7 @@ wheels = [
 [[package]]
 name = "realtimestt"
 version = "0.3.104"
-source = { registry = "https://pypi.org/simple" }
+source = { directory = "../../projects/RealtimeSTT" }
 dependencies = [
     { name = "faster-whisper" },
     { name = "halo" },
@@ -5508,9 +5581,21 @@ dependencies = [
     { name = "websocket-client" },
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/29/15/70c63317462a153ae46a1857e35b21c4de94729f56d8f1b899fbc5ff3b52/realtimestt-0.3.104.tar.gz", hash = "sha256:96bafae0e839c3b60729462cf760c5fc104569c9839fc1071b5afecc1a2b351f", size = 118257, upload-time = "2025-05-03T21:47:33.78Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/cf/24/df28da0f3c5f0d4760e1492e7cee937e0aa72897d4cc41a36ee8c46af5c1/realtimestt-0.3.104-py3-none-any.whl", hash = "sha256:d0a4030551afa3d54b729d94f8a23cca800ef0b21e7778e84ab7ece014c9135f", size = 110633, upload-time = "2025-05-03T21:47:32.59Z" },
+
+[package.metadata]
+requires-dist = [
+    { name = "faster-whisper", specifier = "==1.1.1" },
+    { name = "halo", specifier = "==0.0.31" },
+    { name = "openwakeword", specifier = ">=0.4.0" },
+    { name = "pvporcupine", specifier = "==1.9.5" },
+    { name = "pyaudio", specifier = "==0.2.14" },
+    { name = "scipy", specifier = "==1.15.2" },
+    { name = "soundfile", specifier = "==0.13.1" },
+    { name = "torch", specifier = ">=2.7.1" },
+    { name = "torchaudio", specifier = ">=2.7.1" },
+    { name = "webrtcvad-wheels", specifier = "==2.0.14" },
+    { name = "websocket-client", specifier = "==1.8.0" },
+    { name = "websockets", specifier = "==15.0.1" },
 ]
 
 [[package]]
@@ -6257,6 +6342,7 @@ 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 = "pynput" },
     { name = "pyperclip" },
     { name = "python-doctr" },
     { name = "realtimestt" },
@@ -6266,6 +6352,9 @@ dependencies = [
 ]
 
 [package.optional-dependencies]
+keyboard = [
+    { name = "pynput" },
+]
 screenshot-all = [
     { name = "mss" },
     { name = "pyautogui" },
@@ -6294,16 +6383,18 @@ requires-dist = [
     { name = "pillow", specifier = ">=11.1.0" },
     { name = "pyautogui", marker = "extra == 'screenshot-all'", specifier = ">=0.9.54" },
     { name = "pyautogui", marker = "extra == 'screenshot-full'", specifier = ">=0.9.54" },
+    { name = "pynput", specifier = ">=1.7.6" },
+    { name = "pynput", marker = "extra == 'keyboard'", specifier = ">=1.7.6" },
     { name = "pyperclip", specifier = ">=1.9.0" },
     { name = "pyscreenshot", marker = "extra == 'screenshot-all'", specifier = ">=3.1" },
     { name = "pyscreenshot", marker = "extra == 'screenshot-multi'", specifier = ">=3.1" },
     { name = "python-doctr", specifier = ">=0.8.0" },
-    { name = "realtimestt", specifier = ">=0.3.104" },
+    { name = "realtimestt", directory = "../../projects/RealtimeSTT" },
     { name = "rich", specifier = ">=13.0.0" },
     { name = "rumps", specifier = ">=0.4.0" },
     { name = "typer", specifier = ">=0.12.0" },
 ]
-provides-extras = ["screenshot-fast", "screenshot-full", "screenshot-multi", "screenshot-all"]
+provides-extras = ["screenshot-fast", "screenshot-full", "screenshot-multi", "screenshot-all", "keyboard"]
 
 [package.metadata.requires-dev]
 dev = [{ name = "open-webui", specifier = ">=0.6.5" }]