Update app.py

app.py

@@ -3,6 +3,8 @@ from gtts import gTTS
 import os
 import speech_recognition as sr
 from tempfile import NamedTemporaryFile
+import threading
+import time
 
 # Initialize the recognizer
 recognizer = sr.Recognizer()
@@ -15,6 +17,7 @@ menu_items = {
 }
 cart = []
 
+# Helper Functions
 def text_to_speech(text):
     """Convert text to speech and provide an audio file."""
     tts = gTTS(text=text, lang='en')
@@ -30,6 +33,7 @@ def read_menu():
     menu_text += "Please tell me the items you want to add to your cart."
     return menu_text
 
+# Command Processing
 def process_audio_command(audio_path):
     """Process the user's audio command."""
     global cart
@@ -65,23 +69,41 @@ def process_audio_command(audio_path):
 
     return "Sorry, I didn't understand that. Please try again."
 
-# Define the continuous conversation function
-def conversation_loop(audio_path):
-    """Continuous conversation handling for dynamic interactions."""
-    user_response = process_audio_command(audio_path)
-    return user_response, text_to_speech(user_response)
+# Continuous Conversation Loop
+def continuous_conversation():
+    """Continuously listen to and respond to user commands."""
+    while True:
+        with NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio:
+            try:
+                print("Listening...")
+                with sr.Microphone() as source:
+                    recognizer.adjust_for_ambient_noise(source)
+                    audio = recognizer.listen(source)
+                    with open(temp_audio.name, "wb") as f:
+                        f.write(audio.get_wav_data())
+                response = process_audio_command(temp_audio.name)
+                print(response)
+                audio_response = text_to_speech(response)
+                os.system(f"mpg123 {audio_response}")
+            except Exception as e:
+                print("Error processing audio input.")
 
+# Gradio Interface
 with gr.Blocks() as app:
     gr.Markdown("# Voice-Activated Restaurant Menu System")
     gr.Markdown("Speak your command to interact with the menu dynamically.")
 
     with gr.Row():
         audio_input = gr.Audio(label="Speak Your Command", type="filepath")
-        text_output = gr.Textbox(label="Transcribed Command")
-        response_text = gr.Textbox(label="Response Text")
-        audio_output = gr.Audio(label="Assistant Response")
+        response_text = gr.Textbox(label="Assistant Response")
+        audio_output = gr.Audio(label="Assistant Voice Response")
 
-    audio_input.change(conversation_loop, inputs=audio_input, outputs=[response_text, audio_output])
+    def handle_conversation(audio_path):
+        response = process_audio_command(audio_path)
+        return response, text_to_speech(response)
+
+    audio_input.change(handle_conversation, inputs=audio_input, outputs=[response_text, audio_output])
 
 if __name__ == "__main__":
+    threading.Thread(target=continuous_conversation, daemon=True).start()
     app.launch()