This script combines an audio file (like a DJ mix) and a static image (like a mix cover) and into a video file using ffmpeg, suitable for upload to YouTube.

combine_audio_and_image_to_video.py

# This script combines an audio file (like a DJ mix) and a static image (like a mix cover) and into a video file using ffmpeg, suitable for upload to YouTube."
# (C) 2025 Lyjia - released as Creative Commons Attribution-ShareAlike 4.0 International - https://creativecommons.org/licenses/by-sa/4.0/

#!/usr/bin/env python3
import subprocess
import argparse

def create_video(image_path, 
                    audio_path, 
                    output_path,
                    audio_codec,
                    audio_bitrate,
                    video_codec):
    """
    Combines a static image with an audio file into a video file using ffmpeg.

    Args:
        image_path (str): Path to the static image file.
        audio_path (str): Path to the audio file.
        output_path (str): Path for the output video file.
    """
    try:
        # ffmpeg command to create a video
        command = [
            'ffmpeg',
            '-loop', '1',
            '-i', image_path,
            '-i', audio_path,
            '-c:v', video_codec,
            '-c:a', audio_codec,
            '-b:a', audio_bitrate+"k",
            '-pix_fmt', 'yuv420p',
            '-shortest',
            output_path
        ]

        # Run the ffmpeg command
        subprocess.run(command, check=True)
        print(f"Video successfully created: {output_path}")

    except subprocess.CalledProcessError as e:
        print(f"Error occurred while creating the video: {e}")
    except FileNotFoundError:
        print("ffmpeg is not installed or not found in your PATH.")


def main():
    # Parse command-line arguments
    parser = argparse.ArgumentParser(
        description="This script combines an audio file (like a DJ mix) and a static image (like a mix cover) and into a video file using ffmpeg, suitable for upload to YouTube."
    )
    parser.add_argument(
        '-i', '--image', type=str, help="Path to the input static image file"
    )
    parser.add_argument(
        '-a', '--audio', type=str, help="Path to the input audio file"
    )
    parser.add_argument(
        '-o', '--output', type=str, help="Path to the output video file"
    )
    parser.add_argument(
        '--ac', type=str, help="Audio codec to use", default="aac"
    )
    parser.add_argument(
        '--ab', type=str, help="Audio bitrate to use (in kilobits, e.g. '128')", default="128"
    )
    parser.add_argument(
        '--vc', type=str, help="Video codec to use", default="libx264")

    args = parser.parse_args()

    # Call the create_video function with the parsed arguments
    create_video(image_path=args.image, audio_path=args.audio, output_path=args.output, audio_bitrate=args.ab, audio_codec=args.ac, video_codec=args.vc)


if __name__ == "__main__":
    main()