Update app.py

app.py

@@ -2,11 +2,12 @@ import gradio as gr
 from gtts import gTTS
 import os
 import speech_recognition as sr
+from tempfile import NamedTemporaryFile
 
-# Initialize recognizer
+# Initialize the recognizer
 recognizer = sr.Recognizer()
 
-# Menu items
+# Menu items and cart initialization
 menu_items = {
     "biryani": ["Chicken Biryani", "Mutton Biryani", "Vegetable Biryani", "Egg Biryani"],
     "starters": ["Chicken Tikka", "Paneer Tikka", "Fish Fry", "Veg Manchurian"],
@@ -14,84 +15,73 @@ menu_items = {
 }
 cart = []
 
-# Text-to-Speech Function
 def text_to_speech(text):
-    """Convert text to speech and provide audio file."""
+    """Convert text to speech and provide an audio file."""
     tts = gTTS(text=text, lang='en')
-    file_path = "response.mp3"
-    tts.save(file_path)
-    return file_path
+    audio_file = NamedTemporaryFile(delete=False, suffix=".mp3")
+    tts.save(audio_file.name)
+    return audio_file.name
 
-# Read Menu Function
 def read_menu():
-    """Generate the menu text and read it aloud."""
-    menu_text = "Here is the menu. Starting with Biryani options: "
-    for item in menu_items["biryani"]:
-        menu_text += item + ". "
-    menu_text += "Now the Starters: "
-    for item in menu_items["starters"]:
-        menu_text += item + ". "
-    menu_text += "Finally, Drinks: "
-    for item in menu_items["drinks"]:
-        menu_text += item + ". "
-    return menu_text, text_to_speech(menu_text)
+    """Generate and return the menu text."""
+    menu_text = "Here is the menu: \n"
+    for category, items in menu_items.items():
+        menu_text += f"{category.capitalize()}: \n" + ", ".join(items) + "\n"
+    menu_text += "Please tell me the items you want to add to your cart."
+    return menu_text
 
-# Process Voice Command
-def process_command(audio_path):
-    """Process the user's voice command."""
+def process_audio_command(audio_path):
+    """Process the user's audio command."""
+    global cart
     try:
         with sr.AudioFile(audio_path) as source:
-            audio_data = recognizer.record(source)
-            command = recognizer.recognize_google(audio_data).lower()
+            audio = recognizer.record(source)
+            command = recognizer.recognize_google(audio).lower()
     except Exception as e:
-        error_text = "Sorry, I could not process the audio."
-        return "Error", text_to_speech(error_text)
+        return "Sorry, I could not understand. Could you repeat?"
 
     if "menu" in command:
-        menu_text, menu_audio = read_menu()
-        return menu_text, menu_audio
+        return read_menu()
 
     for category, items in menu_items.items():
         for item in items:
             if item.lower() in command:
                 cart.append(item)
-                response_text = f"{item} has been added to your cart."
-                return response_text, text_to_speech(response_text)
+                return f"{item} has been added to your cart."
 
     if "cart" in command:
         if not cart:
-            response_text = "Your cart is empty."
+            return "Your cart is empty."
         else:
-            response_text = "Your cart contains: " + ", ".join(cart)
-        return response_text, text_to_speech(response_text)
+            return "Your cart contains: " + ", ".join(cart)
 
-    if "submit" in command or "done" in command:
+    if "submit" in command or "finalize" in command:
         if not cart:
-            response_text = "Your cart is empty. Add some items before submitting."
+            return "Your cart is empty. Add some items before submitting."
         else:
-            response_text = "Your final order is: " + ", ".join(cart) + ". Thank you for your order!"
+            response = "Your final order is: " + ", ".join(cart) + ". Thank you for your order!"
             cart.clear()
-        return response_text, text_to_speech(response_text)
+            return response
 
-    error_text = "Sorry, I couldn't understand your request."
-    return error_text, text_to_speech(error_text)
+    return "Sorry, I didn't understand that. Please try again."
 
-# Gradio App
-def app():
-    """Create the Gradio interface."""
-    with gr.Blocks() as demo:
-        gr.Markdown("# Voice-Activated Restaurant Menu System")
-        gr.Markdown("Speak your command to interact with the menu system dynamically.")
+# 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)
 
-        with gr.Row():
-            voice_input = gr.Audio(type="filepath", label="Speak Your Command")
-            transcribed_text = gr.Textbox(label="Transcribed Command")
-            response_text = gr.Textbox(label="Response Text")
-            audio_output = gr.Audio(label="Audio Response")
+with gr.Blocks() as app:
+    gr.Markdown("# Voice-Activated Restaurant Menu System")
+    gr.Markdown("Speak your command to interact with the menu dynamically.")
 
-        voice_input.change(fn=process_command, inputs=voice_input, outputs=[response_text, audio_output])
+    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")
 
-    return demo
+    audio_input.change(conversation_loop, inputs=audio_input, outputs=[response_text, audio_output])
 
 if __name__ == "__main__":
-    app().launch()
+    app.launch()