FFmpeg - Merging multiple videos containing chapters into one with chapters from originals

Input: I have two video files, both with embedded chapter marks. I want to combine these files and preserve the chapter marks metadata. I want the second video file's chapter marks to adapt to the runtime of the combined video file. I want to use ffmpeg to achieve this. How do I do it?

Output: Here's how you can do it:

1. Extract Chapter Information: Before merging the videos, extract the chapter metadata. You can use ffprobe (comes with ffmpeg) to get the chapter information from the video files.

Here is the ffprobe command to get the chapters:

ffprobe -loglevel error -select_streams v -show_entries chapter=start_time,end_time,CHAPTERS/tags/title -of csv=p=0 <video-file>

This will output the chapter timestamps and titles as a csv. Repeat this for both files, save the output somewhere, call it chapters1.csv and chapters2.csv.

2. Adjust Chapter Timestamps: Assuming that you have now two CSV files representing chapters from both videos, you will have to adjust the second CSV's timestamps. You can do this by adding the duration of the first video to the start time and end time of the chapters in the second CSV.

You can get the duration of a video file like this:

ffprobe -v error -select_streams v:0 -show_entries stream=duration -of default=noprint_wrappers=1:nokey=1 <video-file>

This will output the duration of the video file in seconds. Add this duration to the start time and end time of all chapters from chapters2.csv.

It's important to note that the duration should be added only to the second video's chapters considering that those would be appended at the end of the first video.

3. Concatenate Videos: Concatenate your videos with ffmpeg - there are different ways depending on whether your videos have the same parameters, but assuming they do a simple command would look like:

ffmpeg -i <input1.mp4> -i <input2.mp4> -filter_complex "[0:v:0][0:a:0][1:v:0][1:a:0]concat=n=2:v=1:a=1[outv][outa]" -map "[outv]" -map "[outa]" <output.mp4>

4. Create a Metadata File: The metadata file contains the chapter information that ffmpeg needs. Following is a template you can use:

;FFMETADATA1
[CHAPTER]
TIMEBASE=1/1000
START=0
END=<duration of first chapter in milliseconds>
title=<title of first chapter>
[CHAPTER]
TIMEBASE=1/1000
START=<start of second chapter in milliseconds>
END=<end of second chapter in milliseconds>
title=<title of second chapter>
...

Replace the START, END, and title sections with the data from your CSV files. Create a metadata file for all chapters.

5. Add Chapter Marks: Finally, use ffmpeg to add the chapter marks to the concatenated video.

ffmpeg -i <concatenated-video> -i <metadata-file> -map_metadata 1 -codec copy <output-video>

Please note: This process involves a lot of manual labor. If you have a programming background, you can consider writing a script to automate most of these tasks. If you do not, you might want to consider using a video editor tool with a graphical user interface specifically built for merging video files and preserving/editing metadata.