Update app.py

app.py

@@ -1,52 +1,70 @@
 import gradio as gr
 import pyttsx3
+import speech_recognition as sr
+from gtts import gTTS
 import os
 
-# Initialize Text-to-Speech engine (you can use gTTS as well if you prefer)
+# Initialize Text-to-Speech engine (pyttsx3 for offline or gTTS for better quality)
 engine = pyttsx3.init()
 
-# Function to convert text to speech
+# Initialize Speech Recognition engine
+recognizer = sr.Recognizer()
+
+# Define Menu items for the restaurant
+menu = {
+    "pizza": "Delicious pepperoni pizza with cheese and sauce.",
+    "burger": "Beef burger with lettuce, tomato, and cheese.",
+    "pasta": "Creamy pasta with garlic and parmesan.",
+    "salad": "A healthy vegetable salad with olive oil dressing."
+}
+
+# Function to convert text to speech using gTTS
 def speak_response(text):
-    engine.say(text)
-    engine.runAndWait()
+    tts = gTTS(text=text, lang='en')
+    tts.save("response.mp3")
+    os.system("start response.mp3")  # Windows; on Linux, use 'mpg321 response.mp3'
 
-# Function to process the speech input
-def process_audio(audio):
-    text = audio['text']
-    speak_response(text)
-    return text
+# Function to listen to user speech and convert it to text
+def listen_input():
+    with sr.Microphone() as source:
+        print("Listening for order...")
+        audio = recognizer.listen(source)
+        try:
+            command = recognizer.recognize_google(audio)
+            print(f"You said: {command}")
+            return command
+        except sr.UnknownValueError:
+            return "Sorry, I didn't understand that. Could you please repeat?"
+        except sr.RequestError:
+            return "Sorry, there was an issue with the speech service."
 
-# Function to handle menu items and return response
+# Function to handle menu interaction and confirm orders
 def handle_order(item):
-    if item.lower() == "pizza":
-        response = "You have selected Pizza. It contains cheese, tomato sauce, and pepperoni."
-    elif item.lower() == "burger":
-        response = "You have selected Burger. It contains beef patty, lettuce, and cheese."
-    else:
-        response = "Sorry, I don't have information about that item."
+    item = item.lower()
+    response = menu.get(item, "Sorry, we don't have that item on the menu.")
     speak_response(response)
     return response
 
-# Gradio Interface setup
+# Gradio interface setup
 def chatbot_interface():
     with gr.Blocks() as demo:
-        # Display the menu logo image (use your image path)
+        # Display menu logo image (optional)
         gr.Image("assets/menu_logo.png", label="Click to speak", elem_id="voice_logo", interactive=True)
 
-        # Microphone input to get user's speech
-        audio_input = gr.Audio(source="microphone", type="numpy", label="Speak your order")
-
-        # Text output for displaying response
+        # Textbox for displaying responses
         output_text = gr.Textbox(label="Assistant Response", interactive=False)
 
-        # Function to process and return speech input
+        # Microphone button to listen to user input
+        audio_input = gr.Audio(source="microphone", type="numpy", label="Speak your order")
+
+        # Handle audio input and provide the appropriate response
         def on_audio_input(audio):
-            user_input = process_audio(audio)
-            response = handle_order(user_input)
-            output_text.update(value=response)
+            user_input = listen_input()  # Convert speech to text
+            response = handle_order(user_input)  # Handle order
+            output_text.update(value=response)  # Display assistant's response
             return response
 
-        # Attach microphone action
+        # Attach microphone action to trigger audio input
         audio_input.change(on_audio_input, inputs=[audio_input], outputs=[output_text])
 
     demo.launch()