ffmpeg -i video0 -i video1 -i video2 -i music -filter_complex
"[0:v]fps=25,scale=1280x720,setpts=PTS-STARTPTS[v0];
"[1:v]fps=25,scale=1280x720,setpts=PTS-STARTPTS[v1];
"[1:v]fps=25,scale=1280x720,setpts=PTS-STARTPTS[v2];
"[v0][v1][v2]concat=n=3:v=1:a=0,format=yuv420p[v]"
-map "[v]" -map 3:a -shortest output

file "/path/to/video0"
file "/path/to/video1"
file "/path/to/video2"

ffmpeg -f concat -i input.txt -i music -shortest output