cv2 wait key (Hoping to make it variable depending on latency)

When using my code bellow (It turns YouTube videos into ASCII with audio) The latency between the audio and video grows bigger each frame (I have tried many different wait times) I was wondering if there is a way to change the code to make it so the wait key changes depending on how much latency there is. I have only been coding for 6 months so sorry if there is any bad code.

import pytube
import os
import cv2
import PIL.Image
import winsound
from moviepy.editor import *
from pydub import AudioSegment
import threading
import time



##################################################


# downloads the youtube video and lets you input the path for where it should be saved

url = input ("Enter the you youtube url: \n\n")

path = input ("Enter the path where you want the youtube video to be saved: \n\n")


try:
    youtube = pytube.YouTube(url)

    streams = youtube.streams.all()

    video = youtube.streams.get_highest_resolution()
    video.download(path)
    print ("Done!")

except:

    print ("\nYoutube video has coppy righted material so it can not be downloaded. Try again with a different video")




##################################################



#locates all the files with the file extension .mp4

for root, dirs, files in os.walk(path):

    for file in files:
        if file.endswith(".mp4"):
            file_name = (file)
            file_path = (os.path.join(root,file))
            
            
            print (file_name)
            print (file_path)


##################################################




mp3_file = (path+"\\")
mp3_file = (mp3_file+"audio.mp3")
mp4_file = (path+"\\")
mp4_file = (mp4_file+file_name)

VideoClip = VideoFileClip(mp4_file)
audioclip = VideoClip.audio
audioclip.write_audiofile(mp3_file)

audioclip.close()

VideoClip.close()

sound = AudioSegment.from_mp3(mp3_file)

sound.export(path+"/audio.wav", format = "wav")



##################################################


def a():

    # Ascii characters used to create the output 
    ASCII_CHARS = ["@", "#", "S", "%", "?", "*", "+", ";", ":", ",", "."]

    def resized_gray_image(image ,new_width=80):
        width,height = image.size
        aspect_ratio = height/width
        new_height = int(aspect_ratio * new_width)
        resized_gray_image = image.resize((new_width,new_height)).convert('L')
        return resized_gray_image

    def pix2chars(image):
        pixels = image.getdata()
        
        characters = "".join([ASCII_CHARS[pixel//25] for pixel in pixels])
        return characters

    def generate_frame(image,new_width=80):
        new_image_data = pix2chars(resized_gray_image(image))

        total_pixels = len(new_image_data)

        ascii_image = "\n".join([new_image_data[index:(index+new_width)] for index in range(0, total_pixels, new_width)])

        sys.stdout.write(ascii_image)
        os.system('cls' if os.name == 'nt' else 'clear')




    cap = cv2.VideoCapture(mp4_file)
    print (cap)
    
    try:    
        while True:


            ret,frame = cap.read()
            cv2.imshow("frame",frame)
          
            generate_frame(PIL.Image.fromarray(frame))
            cv2.waitKey(1)


    except:

        threading.Thread(target=c).start()


##################################################

def b():
    
    winsound.PlaySound(path+"/audio.wav",winsound.SND_FILENAME)


##################################################


def c ():


    os.remove (mp3_file)
    os.remove (mp4_file)
    os.remove (path+"/audio.wav")


threading.Thread(target=a).start()

threading.Thread(target=b).start()