Update app.py

app.py

@@ -1,7 +1,7 @@
 import os
 import google.generativeai as genai
 import speech_recognition as sr
-import pyttsx3
+from gtts import gTTS  # Replacing pyttsx3 with gTTS for text-to-speech
 from dotenv import load_dotenv
 import gradio as gr
 import tempfile
@@ -9,15 +9,12 @@ import tempfile
 # Load environment variables
 load_dotenv()
 
-# Initialize text-to-speech engine
-engine = pyttsx3.init()
-
 def speak_and_save(text):
-    """Use text-to-speech to speak the given text and save it as an audio file."""
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as fp:
+    """Use gTTS to speak the given text and save it as an audio file."""
+    tts = gTTS(text)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as fp:
         audio_path = fp.name
-    engine.save_to_file(text, audio_path)
-    engine.runAndWait()
+    tts.save(audio_path)
     return audio_path
 
 def recognize_speech_from_audio(audio_file):
@@ -86,6 +83,6 @@ def assistant(audio):
 gr.Interface(
     fn=assistant,  # Function to call when the interface is run
     inputs=gr.Audio(type="filepath"),  # Audio input, expecting a file path from the microphone
-    outputs=[gr.Textbox(), gr.Audio(type="filepath")],  # Outputs text and the response audio
+    outputs=[gr.Textbox(), gr.Audio(type="filepath", label="Response Audio")],  # Outputs text and the response audio
     title="Sema Voice Assistant"
 ).launch()