Freepbx Voicemail Transcription Script: AWS Transcribe API

sendmail-aws

#!/bin/sh

# sendmail-aws
#
# Installation instructions
# Copy the content of this file to /usr/sbin/sendmail-aws
# Modify line #69 with your S3 bucket name 
#
# AWS
# ---------------
# Create an AWS account if you don't have one yet.
#
# Create an S3 bucket to store the VM's and transcriptions
#
# Create a role for your AWS instance granting permissions to your S3 bucket, and to AWS transcribe
# Attach that role to your instance so the AWS cli doesn't need to have credentials assigned to it within the instance
#
# From the Linux command line on the FreePBX machine
# -------------------------------------------
#
# Verify that you have the following (by simply running the command) and if not use yum install;
#    aws
#    jq
#    sox
#    flac
#    dos2unix -V
#
# Follow the instructions to install aws cli https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html
#
# Run the following commands on FreePBX;
#
#    curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip"
#    unzip -qq awscliv2.zip
#    sudo ./aws/install
#    sudo yum install jq
#    cd /usr/sbin/
#    chown asterisk:asterisk sendmail-aws
#    chmod 744 sendmail-aws
#
#
# Open FreePBX web interface
#     Go to Settings > Voicemail Admin > Settings > Email Config
#     Change Mail Command to: /usr/sbin/sendmail-aws
#     Submit and apply changes
#
# 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
# current version: https://gist.github.com/sniper7kills/6775dacd2b2b0892ec4932975ee04aa3
#
# Notes: This is a script modified from the original to work with FreePBX so that email notifications sent from
#        Asterisk voicemail contain a speech to text transcription provided by AWS Transcribe API
#
# 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:
# 2023-01-30  Modified for use with AWS Transcribe instead of of Google
# 2021-05-06  Add fix by dcat127: trim flac file to 59 seconds
# 2020-08-27  Add fix by chrisduncansn
#             Minor edit in instruction wording
# 2020-05-27  Add instructions from sr10952
#             Add export fix by levishores 
# 2019-02-27  Initial commit by tony722

# set PATH
PATH="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
S3_BUCKET="freepbx-transcriptions"

# 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 the wav file to FLAC
	sox -G stream.part3.wav --channels=1 --bits=16 --rate=8000 stream.part3.flac trim 0 59

	# 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

	# save voicemail in tmp folder in case of trouble
	# TMPMP3=$(mktemp -u /tmp/msg_XXXXXXXX.mp3)
	# cp "stream.part3.mp3" "$TMPMP3"

    # Create a string based on the current date and time
    current_date_time="$(date +%Y-%m-%d_%H-%M-%S)"

    # Upload to the S3 Bucket
    aws s3 cp stream.part3.mp3 s3://$S3_BUCKET/$current_date_time


    # Start the transcription job
    output=$(aws transcribe start-transcription-job \
    --transcription-job-name $current_date_time \
    --language-code en-US \
    --media-format mp3 \
    --media MediaFileUri=s3://$S3_BUCKET/$current_date_time \
    --output-bucket-name $S3_BUCKET)

    # Wait for the transcription to finish
    JOB_COMPLETED=false
    while [ "$JOB_COMPLETED" = false ]; do
        JOB_STATUS=$(aws transcribe get-transcription-job \
            --transcription-job-name $current_date_time \
            --query 'TranscriptionJob.TranscriptionJobStatus' \
            --output text)
        if [ "$JOB_STATUS" = "COMPLETED" ]; then
            JOB_COMPLETED=true
        else
            sleep 5
        fi
    done

    # Get the transcription result
    aws s3 cp s3://$S3_BUCKET/$current_date_time.json .

    # Get the transcription result
    FILTERED=$(jq -r '.results.transcripts[].transcript' $current_date_time.json)
	 	   
	# generate first part of mail body, converting it to LF only
	mv stream.part stream.new
	cat stream.part1 >> stream.new
	sed '$d' < stream.part2 >> stream.new

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

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

	# end of message body
	tail -1 stream.part2 >> stream.new

	# 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

# remove the files uploaded to s3
aws s3 rm s3://$S3_BUCKET/$current_date_time
aws s3 rm s3://$S3_BUCKET/$current_date_time.json
aws transcribe delete-transcription-job --transcription-job-name $current_date_time