[Python] Can anyone help me speeding my pygame and edge-tts code

So this is my code

import asyncio
import edge_tts
import os
import pygame

def speak(audio):
VOICES = ['en-AU-NatashaNeural', 'en-AU-WilliumNeural', 'en-CA-ClaraNeural', 'en-CA-LiamNeural', 'en-GB-LibbyNeural', 'en-GB-MaisieNeural', 'en-US-AndrewMultilingualNeural']
COMMAND = f'edge-tts --voice "{VOICES[6]}" --text "{audio}" --write-media "audio.mp3"'
os.system(COMMAND)
pygame.init()
pygame.mixer.init()
pygame.mixer.music.load("audio.mp3")

try:
pygame.mixer.music.play()

while pygame.mixer.music.get_busy():
pygame.time.Clock().tick(10)

except Exception as e:
print(e)

finally:
pygame.mixer.music.stop()
pygame.mixer.quit()


Now when I use this, it makes a audio.mp3 file and I use it in my program. but when I use multiples together like this:

Speak("Hello")
Speak("How are you?")


It takes like 2 to 3 secs between this 2 line to run because of pygame. Now can you make it faster for me and give it too me. I don't know how can I do that.

Continue reading...