app.py

import gradio as gr
from utils.stt import speech_to_text
from utils.nlp import process_query
from utils.tts import text_to_speech

# Load intents and other configurations
import json
with open("intents.json", "r") as f:
    intents = json.load(f)

def voice_agent(audio):
    # Step 1: Convert speech to text
    query = speech_to_text(audio)

    # Step 2: Process the query and get a response
    response = process_query(query, intents)

    # Step 3: Convert the response to speech
    audio_response = text_to_speech(response)

    return response, audio_response

# Gradio interface
interface = gr.Interface(
    fn=voice_agent,
    inputs=gr.Audio(source="microphone", type="filepath"),
    outputs=[
        gr.Textbox(label="Agent Response"),
        gr.Audio(label="Voice Response")
    ],
    title="Hotel Booking Voice Agent"
)

if __name__ == "__main__":
    interface.launch()