Audiobook Creator

audiobook.py

#!/usr/bin/env python3

import glob
import os
import subprocess
import sys

def die(msg):
    print(f"Error: {msg}", file=sys.stderr)
    sys.exit(1)

mp3s = sorted(glob.glob("*.mp3"))
if not mp3s:
    die("No .mp3 files found in current directory")

covers = (
    sorted(glob.glob("*.jpg")) +
    sorted(glob.glob("*.jpeg")) +
    sorted(glob.glob("*.JPG")) +
    sorted(glob.glob("*.JPEG"))
)
if not covers:
    die("No .jpg/.jpeg cover image found in current directory")

cover = covers[0]

book = input("Book name: ").strip()
author = input("Author: ").strip()

if not book:
    die("Book name cannot be empty")
if not author:
    die("Author cannot be empty")

def duration_ms(path):
    try:
        out = subprocess.check_output(
            [
                "ffprobe",
                "-v", "error",
                "-show_entries", "format=duration",
                "-of", "default=nw=1:nk=1",
                path
            ],
            text=True
        ).strip()
        return int(round(float(out) * 1000))
    except Exception as e:
        die(f"Failed to read duration of {path}: {e}")

# Write concat list
with open("list.txt", "w", encoding="utf-8") as f:
    for p in mp3s:
        f.write("file '" + p.replace("'", r"'\''") + "'\n")

# Write chapters
current = 0
with open("chapters.ffmeta", "w", encoding="utf-8") as f:
    f.write(";FFMETADATA1\n")
    for p in mp3s:
        dur = max(duration_ms(p), 1)
        title = os.path.splitext(os.path.basename(p))[0]
        f.write("\n[CHAPTER]\n")
        f.write("TIMEBASE=1/1000\n")
        f.write(f"START={current}\n")
        f.write(f"END={current + dur}\n")
        f.write(f"title={title}\n")
        current += dur

output = f"{book}.m4b"

cmd = [
    "ffmpeg", "-y",
    "-f", "concat", "-safe", "0", "-i", "list.txt",
    "-i", "chapters.ffmeta",
    "-i", cover,
    "-map", "0:a",
    "-map", "2:v",
    "-map_metadata", "1",
    "-map_chapters", "1",
    "-c:a", "aac",
    "-b:a", "128k",
    "-c:v", "copy",
    "-disposition:v:0", "attached_pic",
    "-metadata", f"title={book}",
    "-metadata", f"album={book}",
    "-metadata", f"artist={author}",
    "-metadata", f"album_artist={author}",
    "-movflags", "+faststart",
    output
]

print(f"Cover image : {cover}")
print(f"Output file : {output}")
print("Building audiobook…")

subprocess.run(cmd, check=True)

print("Done.")

Takes all mp3's in the local directory (make sure that they are named in order!) and the jpg file in the directory (or first one if there are multiples), to output an audiobook m4b with chapters. Just a quick script for this, don't blame me if something goes wrong.