Python script to create video from the specified audio track and an image

create_video.py

import argparse
import numpy as np
from PIL import Image
from moviepy.editor import *
import os
import errno

TARGET_WIDTH = 1920
TARGET_HEIGHT = 1080
TARGET_FPS = 24
FRAME_BASE_NUMBER = 100

def create_image(image_file, target_width, target_height):
    # Create a black background image
    image = Image.new('RGB', (target_width, target_height), (0, 0, 0))

    # Load image and resize to fit on the black background
    if image_file:
        image_pil = Image.open(image_file)
        image_pil.thumbnail((target_width, target_height))
        width, height = image_pil.size

        offset = ((target_width - width) // 2, (target_height - height) // 2)
        image.paste(image_pil, offset)

    image_name = "tmp_image.png"
    image.save(image_name, format="PNG")
        
    return image_name

# Render a 100 frames long video using an image file with MoviePy
def render_video(image_file, output_file, frame_number, fps):
    clip_list = []
    image_clip = ImageClip(image_file)
    
    for i in range(frame_number):
        frame = image_clip.set_duration(1/fps)
        clip_list.append(frame)
    
    final_clip = concatenate_videoclips(clip_list)
    final_clip.write_videofile(output_file, fps=fps)

# Create temporary video files to concatenate multiple times to reach the desired frame number
def create_temporary_video(image_file, frame_number, fps):
    num_videos = frame_number // FRAME_BASE_NUMBER
    extra_frames = frame_number % FRAME_BASE_NUMBER

    with open('mylist.txt', 'w') as f:
        render_video(image_file, f'temp_video.mp4', FRAME_BASE_NUMBER, fps)
        for _ in range(num_videos):
            f.write(f"file 'temp_video.mp4'\n")
    
    if extra_frames > 0:
        render_video(image_file, f'temp_video_extra.mp4', extra_frames, fps)
        with open('mylist.txt', 'a') as f:
            f.write(f"file 'temp_video_extra.mp4'\n")

    os.remove(image_file)
    
    return num_videos

def silentremove(filename):
    if os.path.isfile(filename):
        os.remove(filename)
	
def cleanup(temp_files_list):
	for file in temp_files_list:
		silentremove(file)

def create_video(audio_file, image_file, output_file, width, height, fps):
    audio = AudioFileClip(audio_file)
    frame_number = int(audio.duration * fps)
    
    image_file = create_image(image_file, width, height)

    # Create temporary video files as necessary to reach the desired frame number
    num_videos_needed = create_temporary_video(image_file, frame_number, fps)

    # Concatenate the temporary video files using ffmpeg
    try:
        os.system('ffmpeg -y -f concat -safe 0 -i mylist.txt -c copy temp_concat.mp4')
        os.system(f'ffmpeg -y -i temp_concat.mp4 -i \"{audio_file}\" -map 0 -map 1:a -c:v copy -shortest \"{output_file}\"')
    except:
        raise
    finally:
        cleanup(["temp_video.mp4", "temp_concat.mp4", "temp_video_extra.mp4", "mylist.txt"])

    print(f"Video has been successfully rendered and saved as {output_file}")

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Create a video from an audio file and an image.")
    parser.add_argument("-a", "--audio", required=True, help="Path to audio file")
    parser.add_argument("-i", "--image", help="Path to image file")
    parser.add_argument("--width", help="Output video width", type=int, default=TARGET_WIDTH)
    parser.add_argument("--height", help="Output video height", type=int, default=TARGET_HEIGHT)
    parser.add_argument("-f", "--fps", help="Output video FPS", type=int, default=TARGET_FPS)
    parser.add_argument("-o", "--output", required=True, help="Output file name")

    args = parser.parse_args()

    create_video(args.audio, args.image, args.output, args.width, args.height, args.fps)