Update app.py

app.py

@@ -1,55 +1,35 @@
 import gradio as gr
-import pyttsx3
-import speech_recognition as sr
-from transformers import pipeline
+from utils.stt import speech_to_text
+from utils.nlp import process_query
+from utils.tts import text_to_speech
 
-# Initialize Text-to-Speech engine
-engine = pyttsx3.init()
-engine.setProperty('rate', 150)
+# Load intents and other configurations
+import json
+with open("intents.json", "r") as f:
+    intents = json.load(f)
 
-# Load a conversational AI model
-chatbot = pipeline("conversational", model="microsoft/DialoGPT-medium")
+def voice_agent(audio):
+    # Step 1: Convert speech to text
+    query = speech_to_text(audio)
 
-def tts_response(user_query):
-    """Generate AI response, convert to speech, and return text."""
-    try:
-        response = chatbot(user_query)
-        bot_reply = response[0]['generated_text']
-        engine.say(bot_reply)
-        engine.runAndWait()
-        return bot_reply
-    except Exception as e:
-        return f"Error: {str(e)}"
+    # Step 2: Process the query and get a response
+    response = process_query(query, intents)
 
-def stt_to_tts(audio):
-    """Convert speech to text, process with AI, then convert response to speech."""
-    recognizer = sr.Recognizer()
-    try:
-        with sr.AudioFile(audio) as source:
-            audio_data = recognizer.record(source)
-            user_query = recognizer.recognize_google(audio_data)
-            return tts_response(user_query)
-    except sr.UnknownValueError:
-        return "Sorry, I could not understand the audio."
-    except sr.RequestError as e:
-        return f"Request error from Speech Recognition service; {e}"
+    # Step 3: Convert the response to speech
+    audio_response = text_to_speech(response)
+
+    return response, audio_response
 
 # Gradio interface
-def gradio_ui():
-    with gr.Blocks() as app:
-        gr.Markdown("## AI Voice Agent")
-        with gr.Tab("Text-to-Speech"):
-            user_query = gr.Textbox(label="Your Query")
-            response = gr.Textbox(label="AI Response", interactive=False)
-            submit_button = gr.Button("Submit")
-            submit_button.click(tts_response, inputs=user_query, outputs=response)
-        with gr.Tab("Speech-to-Speech"):
-            audio_input = gr.Audio(source="microphone", type="filepath", label="Speak Now")
-            audio_response = gr.Textbox(label="AI Response")
-            audio_button = gr.Button("Submit")
-            audio_button.click(stt_to_tts, inputs=audio_input, outputs=audio_response)
-    return app
+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__":
-    app = gradio_ui()
-    app.launch()
+    interface.launch()