ffmpeg -i voice.wav -i music.wav -filter_complex "[1:a]volume=0.15[m];[0:a][m]amix=inputs=2:duration=first:normalize=0[out]" -map "[out]" mixed.wav
ffmpeg -i mixed.wav -af loudnorm=I=-16:TP=-1.5:LRA=11:print_format=json -f null -