sendmail-openai

#!/bin/bash
# sendmail-apenai
#
# Installation instructions
# https://github.com/VitalPBX/vitalpbx-voicemail-transcription-openai/blob/main/README.md
#
# Special thanks to:
# Original source created by N. Bernaerts: https://github.com/NicolasBernaerts/debian-scripts/tree/master/asterisk
# modified per: https://jrklein.com/2015/08/17/asterisk-voicemail-transcription-via-ibm-bluemix-speech-to-text-api/
# modified per: https://gist.github.com/lgaetz/2cd9c54fb1714e0d509f5f8215b3f5e6
# modified per: https://gist.github.com/tony722/7c6d86be2e74fa10a1f344a4c2b093ea
#
# License: There are no explicit license terms on the original script or on the blog post with modifications
#          I'm assumig GNU/GPL2+ unless notified otherwise by copyright holder(s)
# Version History:
# 2023-05-04  Adapts to work with VitalPBX 4 and OpenAI
#
API_KEY=""
API_URL="https://api.openai.com/v1/audio/transcriptions"
# set PATH
PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"

# save the current directory
pushd .
 
# create a temporary directory and cd to it
TMPDIR=$(mktemp -d)
cd $TMPDIR
 
# dump the stream to a temporary file
cat >> stream.org
 
# get the boundary
BOUNDARY=$(grep "boundary=" stream.org | cut -d'"' -f 2)
 
# if mail has no boundaries, assume no attachment
if [ "$BOUNDARY" = "" ]
	
then
	# send the original stream
	mv stream.org stream.new
else
	# cut the original stream into parts
	# stream.part  - header before the boundary
	# stream.part1 - header after the bounday
	# stream.part2 - body of the message
	# stream.part3 - attachment in base64 (WAV file)
	# stream.part4 - footer of the message
	awk '/'$BOUNDARY'/{i++}{print > "stream.part"i}' stream.org
 
	# cut the attachment into parts
	# stream.part3.head - header of attachment
	# stream.part3.wav.base64 - wav file of attachment (encoded base64)
	sed '7,$d' stream.part3 > stream.part3.wav.head
	sed '1,6d' stream.part3 > stream.part3.wav.base64

	# convert the base64 file to a wav file
	dos2unix -o stream.part3.wav.base64
	base64 -di stream.part3.wav.base64 > stream.part3.wav

	# convert to MP3
	sox stream.part3.wav stream.part3-pcm.wav
	lame -m m -b 24 stream.part3-pcm.wav stream.part3.mp3 
	base64 stream.part3.mp3 > stream.part3.mp3.base64

	# create mp3 mail part
	sed 's/x-[wW][aA][vV]/mpeg/g' stream.part3.wav.head | sed 's/.[wW][aA][vV]/.mp3/g' > stream.part3.new
	dos2unix -o stream.part3.new 
	unix2dos -o stream.part3.mp3.base64
	cat stream.part3.mp3.base64 >> stream.part3.new

	# convert audio to text and get result
	RESULT=`curl --request POST --url $API_URL --header "Authorization: Bearer $API_KEY" --header 'Content-Type: multipart/form-data' --form file=@stream.part3.mp3 --form response_format=text --form model=whisper-1`
	 	   
	# generate first part of mail body, converting it to LF only
	mv stream.part stream.new
	cat stream.part1 >> stream.new
	cat stream.part2 >> stream.new

	# beginning of transcription section
	echo "" >> stream.new
	echo "--- OpenAI Transcription ---" >> stream.new

	# append result of transcription
	if [ -z "$RESULT" 	]
	then
	  echo "--- OpenAI was unable to recognize any speech in audio data ---" >> stream.new
	else
	  echo "$RESULT" >> stream.new
	fi

	# add converted attachment  
	cat stream.part3.new >> stream.new

	# append end of mail body, converting it to LF only
	echo "" >> stream.tmp
	echo "" >> stream.tmp
	cat stream.part4 >> stream.tmp
	dos2unix -o stream.tmp
	cat stream.tmp >> stream.new
 
fi
 
# send the mail thru sendmail
cat stream.new | sendmail -t
 
# go back to original directory
popd
 
# remove all temporary files and temporary directory
rm -Rf $TMPDIR