Extract audio from video and strip all metadata

extract-audio-strip-metadata.sh

#!/usr/bin/bash

# 20221216 init

# published as https://berlin.social/@wikinaut/109541495757480127

compressionquality="-q:a 7 -joint_stereo 1"
mono="-ac 1"

red="\e[1;31m"
yellow="\e[1;33m"
nocol="\e[0m"

if [ $# -lt 1 ]; then
	echo "Extract audio from video and strip metadata"
	echo
	echo "Usage:"
	echo "extract-audio-strip-metadata.sh infile.mp4"
	echo
	echo -e "1. Generate quality-controlled (${red}${compressionquality}${nocol}) stereo and mono audio-only versions: ${yellow}mp3, mono.mp3${nocol}"
	echo -e "2. Strip meta data of video and audio versions: ${yellow}stripped.mp4, stripped.mp3, mono.stripped.mp3${nocol}"
	exit
fi

# https://stackoverflow.com/questions/9913032/how-can-i-extract-audio-from-video-with-ffmpeg
# https://trac.ffmpeg.org/wiki/Encode/MP3
#
# lame option 	Average kbit/s 	Bitrate range kbit/s 		ffmpeg option
# -b 320 	320 		320 CBR (non VBR) example 	-b:a 320k 	(NB this is 32KB/s, or its max)
# -V 0 		245 		220-260 			-q:a 0		(NB this is VBR from 220 to 260 KB/s)
# -V 1 		225 		190-250 			-q:a 1
# -V 2 		190 		170-210 			-q:a 2
# -V 3 		175 		150-195			 	-q:a 3
# -V 4 		165 		140-185 			-q:a 4
# -V 5 		130 		120-150 			-q:a 5
# -V 6 		115 		100-130			 	-q:a 6
# -V 7 		100 		80-120 				-q:a 7
# -V 8 		85 		70-105 				-q:a 8
# -V 9 		65 		45-85 				-q:a 9

ext=${1#*.} 
video=0

if [ "${ext,,}" = "mp4" ] ; then
	# echo ${1#*.}
	video=1
fi

stripmeta="-c copy -fflags +bitexact -flags:v +bitexact -flags:a +bitexact -write_xing 0 -id3v2_version 0"

# Create a meta-data stripped version of the input file

ffmpeg -i "$1" $stripmeta "${1%.*}.stripped.${1#*.}"

# Create an audio-only file of a certain quality
# and create a meta-data stripped version

ffmpeg -i "$1" $compressionquality -map a "${1%.*}.mp3"
ffmpeg -i "${1%.*}.mp3" $stripmeta "${1%.*}.stripped.mp3"

# Create mono version
# downmix both channels to avoid that any out of phase stereo signal will cancel out.
# The following filtergraph brings out of phase stereo in phase prior to downmixing:
# https://trac.ffmpeg.org/wiki/AudioChannelManipulation

downmix="-af asplit[a],aphasemeter=video=0,ametadata=select:key=lavfi.aphasemeter.phase:value=-0.005:function=less,pan=1c|c0=c0,aresample=async=1:first_pts=0,[a]amix"

ffmpeg -i "$1" $downmix $compressionquality $mono -map a "${1%.*}.mono.mp3"

ffmpeg -i "${1%.*}.mono.mp3" $stripmeta "${1%.*}.mono.stripped.mp3"