Create main.py

main.py

@@ -0,0 +1,105 @@
+import os
+import google.generativeai as genai
+import speech_recognition as sr
+import pyttsx3
+from dotenv import load_dotenv
+import tkinter as tk
+from tkinter import messagebox
+
+# Load environment variables
+load_dotenv()
+
+# Initialize text-to-speech engine
+engine = pyttsx3.init()
+
+def speak(text):
+    """Use text-to-speech to speak the given text."""
+    engine.say(text)
+    engine.runAndWait()
+
+def recognize_speech(timeout=5):
+    """Capture and recognize speech from the microphone with a timeout."""
+    recognizer = sr.Recognizer()
+    with sr.Microphone() as source:
+        print("Listening for a wake-up command...")
+        audio = recognizer.listen(source, timeout=timeout)
+        print("Audio captured.")
+        try:
+            command = recognizer.recognize_google(audio)
+            print(f"You said: {command}")
+            return command
+        except sr.UnknownValueError:
+            print("Could not understand audio.")
+            return None
+        except sr.RequestError:
+            speak("Sorry, there was an error with the speech recognition service.")
+            print("Request error.")
+            return None
+
+def process_command(command):
+    """Generate a response based on the voice command using the AI model."""
+    if command:
+        response = model.generate_content([command])
+        reply = response.text.strip()
+        speak(reply)
+        print(f"AI Response: {reply}")
+        return reply
+
+# GUI Functions
+def start_listening():
+    command = recognize_speech(timeout=5)
+    
+    if command and wake_word in command.lower():
+        speak("How can I assist you?")
+        result_label.config(text="Wake word detected! Listening for further commands...")
+        command = recognize_speech(timeout=5)
+        if command:
+            if "stop listening" in command.lower():
+                speak("Goodbye.")
+                result_label.config(text="Voice assistant stopped.")
+            else:
+                response = process_command(command)
+                result_label.config(text=f"Response: {response}")
+    else:
+        result_label.config(text="Wake word not detected.")
+
+# Main Code with Generative AI Setup
+api_key = os.getenv("MY_API_KEY")
+
+if api_key is None:
+    raise ValueError("API key not found in environment variables")
+
+# Configure the AI model
+genai.configure(api_key=api_key)
+
+generation_config = {
+    "temperature": 1,
+    "top_p": 0.95,
+    "top_k": 64,
+    "max_output_tokens": 8192,
+    "response_mime_type": "text/plain",
+}
+
+model = genai.GenerativeModel(
+    model_name="gemini-1.5-flash-8b-exp-0827",
+    generation_config=generation_config,
+)
+
+wake_word = "sema"
+
+# Create the GUI
+root = tk.Tk()
+root.title("Sema Voice Assistant")
+
+# Create UI elements
+title_label = tk.Label(root, text="SEMA AI", font=("Arial", 16))
+title_label.pack(pady=10)
+
+start_button = tk.Button(root, text="Start Listening", command=start_listening, font=("Arial", 14))
+start_button.pack(pady=10)
+
+result_label = tk.Label(root, text="", font=("Arial", 12))
+result_label.pack(pady=10)
+
+# Run the GUI loop
+root.mainloop()