Update app.py

app.py

@@ -2,9 +2,12 @@ import gradio as gr
 import speech_recognition as sr
 from gtts import gTTS
 import os
-from playsound import playsound
+import pygame  # Use pygame for playing audio
 from transformers import pipeline
 
+# Initialize pygame for audio playback
+pygame.mixer.init()
+
 # Initialize recognizer for speech recognition
 recognizer = sr.Recognizer()
 
@@ -30,7 +33,7 @@ def process_order(order):
 def recognize_speech(audio):
     try:
         # If audio is from file, use SpeechRecognition to convert speech to text
-        if isinstance(audio, str):  # Audio file input
+        if isinstance(audio, str):  # Audio file input (filepath)
             with sr.AudioFile(audio) as source:
                 audio_data = recognizer.record(source)
                 text = recognizer.recognize_google(audio_data)
@@ -45,8 +48,9 @@ def recognize_speech(audio):
         tts = gTTS(text=response, lang='en')
         tts.save("response.mp3")
         
-        # Play the MP3 response using playsound
-        playsound("response.mp3")
+        # Play the MP3 response using pygame
+        pygame.mixer.music.load("response.mp3")
+        pygame.mixer.music.play()
 
         return response
     except Exception as e:
@@ -58,8 +62,8 @@ def create_gradio_interface():
     with gr.Blocks() as demo:
         gr.Markdown("## AI Voice Bot for Food Ordering")
 
-        # Audio Input: User speaks into microphone or uploads a file
-        audio_input = gr.Audio(type="file", label="Speak to the bot (Upload or Record Audio)")
+        # Audio Input: User speaks into microphone or uploads a file (filepath)
+        audio_input = gr.Audio(type="filepath", label="Speak to the bot (Upload or Record Audio)")
 
         # Display the bot's response after recognition
         output_text = gr.Textbox(label="Bot Response")