app.py

import gradio as gr
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()

# 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"],
    "drinks": ["Coke", "Pepsi", "Lemonade", "Mango Juice", "Water"]
}
cart = []

# Helper Functions
def text_to_speech(text):
    """Convert text to speech and provide an audio file."""
    tts = gTTS(text=text, lang='en')
    audio_file = NamedTemporaryFile(delete=False, suffix=".mp3")
    tts.save(audio_file.name)
    return audio_file.name

def read_menu():
    """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

# Command Processing
def process_audio_command(audio_path):
    """Process the user's audio command."""
    global cart
    try:
        with sr.AudioFile(audio_path) as source:
            audio = recognizer.record(source)
            command = recognizer.recognize_google(audio).lower()
    except Exception as e:
        return "Sorry, I could not understand. Could you repeat?"

    if "menu" in command:
        return read_menu()

    for category, items in menu_items.items():
        for item in items:
            if item.lower() in command:
                cart.append(item)
                return f"{item} has been added to your cart."

    if "cart" in command:
        if not cart:
            return "Your cart is empty."
        else:
            return "Your cart contains: " + ", ".join(cart)

    if "submit" in command or "finalize" in command:
        if not cart:
            return "Your cart is empty. Add some items before submitting."
        else:
            response = "Your final order is: " + ", ".join(cart) + ". Thank you for your order!"
            cart.clear()
            return response

    return "Sorry, I didn't understand that. Please try again."

# 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")
        response_text = gr.Textbox(label="Assistant Response")
        audio_output = gr.Audio(label="Assistant Voice Response")

    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()