Update app.py

app.py

@@ -1,10 +1,13 @@
 import gradio as gr
 from gtts import gTTS
-import speech_recognition as sr
 import tempfile
 import os
+import speech_recognition as sr
 
-# Menu items
+# Store cart in a temporary storage
+cart = []
+
+# Define the menu items dynamically
 menu_items = {
     "Pizza": 10.99,
     "Burger": 8.49,
@@ -13,79 +16,91 @@ menu_items = {
     "Soda": 2.49
 }
 
-# Global cart
-cart = []
+def generate_voice_response(text):
+    tts = gTTS(text)
+    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+    temp_file.close()
+    tts.save(temp_file.name)
+    return temp_file.name
 
-def process_audio(audio_file):
+def process_audio(audio_path):
     global cart
     recognizer = sr.Recognizer()
     response = ""
 
     try:
-        # Transcribe user input
-        with sr.AudioFile(audio_file) as source:
+        with sr.AudioFile(audio_path) as source:
             audio = recognizer.record(source)
-            user_input = recognizer.recognize_google(audio)
-            print("User said:", user_input)
-
-        # Process user commands
-        if "menu" in user_input.lower():
-            response = "Here is our menu:\n"
-            for item, price in menu_items.items():
-                response += f"{item}: ${price:.2f}\n"
-            response += "What would you like to add to your cart?"
-
-        elif any(item.lower() in user_input.lower() for item in menu_items):
-            for item in menu_items:
-                if item.lower() in user_input.lower():
-                    cart.append(item)
-                    total = sum(menu_items[i] for i in cart)
-                    response = f"{item} added to your cart. Your current cart includes:\n"
-                    for i in cart:
-                        response += f"- {i}: ${menu_items[i]:.2f}\n"
-                    response += f"Total: ${total:.2f}. Anything else?"
-                    break
-
-        elif "final order" in user_input.lower():
-            if cart:
-                total = sum(menu_items[i] for i in cart)
-                response = "Your final order includes:\n"
-                for i in cart:
-                    response += f"- {i}: ${menu_items[i]:.2f}\n"
-                response += f"Total: ${total:.2f}. Thank you for ordering!"
-                cart.clear()
-            else:
-                response = "Your cart is empty. Please add items to your cart."
+            input_text = recognizer.recognize_google(audio)
+            print("User said:", input_text)
+
+            if "menu" in input_text.lower():
+                response = "Here is our menu:\n"
+                for item, price in menu_items.items():
+                    response += f"{item}: ${price:.2f}\n"
+                response += "\nWhat would you like to add to your cart?"
+
+            elif any(item.lower() in input_text.lower() for item in menu_items):
+                for item in menu_items:
+                    if item.lower() in input_text.lower():
+                        cart.append(item)
+                        total = sum(menu_items[cart_item] for cart_item in cart)
+                        response = f"{item} has been added to your cart. Your current cart includes:\n"
+                        for cart_item in cart:
+                            response += f"- {cart_item}: ${menu_items[cart_item]:.2f}\n"
+                        response += f"\nTotal: ${total:.2f}. Would you like to add anything else?"
+                        break
 
-        else:
-            response = "Sorry, I didn't understand that. Please try again."
+            elif "final order" in input_text.lower() or "submit order" in input_text.lower():
+                if cart:
+                    total = sum(menu_items[cart_item] for cart_item in cart)
+                    response = "Your final order includes:\n"
+                    for item in cart:
+                        response += f"- {item}: ${menu_items[item]:.2f}\n"
+                    response += f"\nTotal: ${total:.2f}. Thank you for ordering!"
+                    cart = []  # Clear cart after finalizing order
+                else:
+                    response = "Your cart is empty. Would you like to order something?"
+
+            elif "stop" in input_text.lower():
+                response = "Stopping voice assistant."
+
+            else:
+                response = "I didn’t quite catch that. Please tell me what you’d like to order."
 
     except sr.UnknownValueError:
-        response = "Sorry, I couldn't understand your voice. Please try again."
+        response = "Sorry, I didn’t catch that. Could you please repeat?"
     except Exception as e:
         response = f"An error occurred: {str(e)}"
 
-    # Generate voice response
-    tts = gTTS(response)
-    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
-    tts.save(temp_file.name)
+    audio_response_path = generate_voice_response(response)
+    return response, audio_response_path
 
-    return response, temp_file.name
+def run_voice_assistant(audio):
+    response, audio_path = process_audio(audio)
+    return response, (audio_path,)
+
+def javascript_autoplay():
+    return """<script>
+    var audio = document.getElementsByTagName('audio')[0];
+    if (audio) {
+        audio.play();
+    }
+    </script>"""
+
+with gr.Blocks() as demo:
+    gr.Markdown("### Voice-Activated Restaurant Assistant")
+
+    with gr.Row():
+        voice_input = gr.Audio(source="microphone", type="filepath", label="Speak Now")
+        assistant_response = gr.Textbox(label="Assistant Response")
 
-# Gradio Interface
-def voice_assistant(audio):
-    response_text, response_audio = process_audio(audio)
-    return response_text, response_audio
+    gr.Markdown("Note: The audio will play automatically.")
 
-# Gradio App
-with gr.Blocks() as app:
-    gr.Markdown("# Voice-Activated Restaurant Assistant")
     with gr.Row():
-        voice_input = gr.Audio(type="filepath", label="Speak Now")
-        output_text = gr.Textbox(label="Assistant Response")
-        output_audio = gr.Audio(label="Audio Response", type="filepath")
+        audio_output = gr.Audio(label="Audio Response")
 
-    voice_input.change(voice_assistant, inputs=voice_input, outputs=[output_text, output_audio])
+    voice_input.change(run_voice_assistant, inputs=voice_input, outputs=[assistant_response, audio_output])
+    gr.HTML(javascript_autoplay())
 
-# Run the app
-app.launch()
+demo.launch()