Psychokiller1888/snipsSuperTTS.sh

## snipsSuperTTS.sh
#!/usr/bin/env bash

# By Psycho
# Shell script to handle different TTS and online / offline connectivity
# This bash script can be set as a custom TTS for snips but also called directly from your skills
# a great way to give more than one personality to your assistant
# Original script: https://gist.github.com/Psychokiller1888/cf10af3220b5cd6d9c92c709c6af92c2

####### COMMON #######
#------------------------------------
# Set your cache path
cache="/home/pi/snipsSuperTTS/cache"
#------------------------------------
# - Install mpg123
# - The cache path is created by the script itself at first run! If you already have the cache directories, make sure to set its owner to "_snips" => sudo chown _snips /home/pi/snipsSuperTTS/cache
# - Edit /etc/snips.toml
# - Set "customtts" as snips-tts provider
# - Add as customtts: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "google", "%%LANG%%", "US", "Wavenet-C", "FEMALE", "%%TEXT%%", "22050"]
# Change "US" to another language country code, "GB" per exemple for a british voice
# You can customize the "Wavenet-C" to another voice of your choice. https://cloud.google.com/text-to-speech/docs/voices / https://docs.aws.amazon.com/polly/latest/dg/voicelist.html
# Offline voices possibilities are: picotts or mycroft
# Fit "FEMALE" to the voice gender you want. Note this is linked to google voices
# You can change the sample rate, the last argument, to your needs
# Restart snips: systemctl restart snips-*
# If you want a total customized experience, you can easily enable both google and amazon and use a different one depending on what you want. Don't be shy, there's no limit
# Note that not all parameters do something depending on the voice you choose. Those are marked with "--" in the provided examples

####### MycroftAI - Mimic #######
# https://github.com/MycroftAI/mimic
# This one is pretty long to install, but hey, the quality compared to pico is worth it!
# Set the following option to True to use Mycroft instead of pico. Don't forget to set the path too
#
# Example: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "mycroft", "%%LANG%%", "--", "slt_hts", "--", "%%TEXT%%", "22050"]
#
# Available voices: aew ahw aup awb axb bdl clb eey fem gka jmk ksp ljm rms rxr slt slt_hts
# Or you can use an external voice on http.
#
# sudo apt-get install gcc make pkg-config automake libtool libasound2-dev
# git clone https://github.com/MycroftAI/mimic.git
# cd mimic
# ./dependencies.sh --prefix="/usr/local"
# ./autogen.sh
# ./configure --prefix="/usr/local"
# make
# sudo /sbin/ldconfig
# make check
useMycroft=false
mycroftPath="/home/pi/mimic"


####### GOOGLE #######
# Install Google SDK: https://cloud.google.com/text-to-speech/docs/quickstart-protocol
# Follow point 6. to initialize the sdk after creating your service account
# Get your api key from the console https://console.developers.google.com
# Uncomment the following and set it accordingly:
#
#googleWavenetAPIKey=""
#
# Example: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "google", "%%LANG%%", "US", "Wavenet-C", "FEMALE", "%%TEXT%%", "22050"]

###### AMAZON #######
# Install Amazon sdk
# curl "https://s3.amazonaws.com/aws-cli/awscli-bundle.zip" -o "awscli-bundle.zip"
# unzip awscli-bundle.zip
# ./awscli-bundle/install -i /usr/local/aws -b /usr/local/bin/aws
# Uncomment the following lines and set them accordingly:
#
#export AWS_ACCESS_KEY_ID=""
#export AWS_SECRET_ACCESS_KEY=""
#export AWS_DEFAULT_REGION="eu-central-1"
#awscli='/usr/local/bin/aws'
#
# command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "amazon", "%%LANG%%", "US", "Joanna", "--", "%%TEXT%%", "22050"]
#
####################################################################################################

outfile="$1"
service="$2"
lang="$3"
country="$4"
voice="$5"
gender="$6"
text="$7"
sampleRate="$8"

if [ "$service" = "mycroft" ] || [ "$service" = "picotts" ]; then
    status="offline"
else
    echo -e "GET http://google.com HTTP/1.0\n\n" | nc google.com 80 > /dev/null 2>&1
    if [ $? -eq 0 ]; then
        status="online"
    else
        status="offline"
    fi
    # Alternative for some people having problem pinging google.com. Comment the above and uncomment the following
    #wget -q --tries=1 --timeout=1 --spider http://google.com
    #if [[ $? -eq 0 ]]; then
    #    status="online"
    #else
    #    status="offline"
    #fi
fi

function picotts() {
    case "$lang" in
        *en*)
            lang="en-US";;
        *de*)
            lang="de-DE";;
        *es*)
            lang="es-ES";;
        *fr*)
            lang="fr-FR";;
        *it*)
            lang="it-IT";;
        *)
            lang="en-US";;
        esac
    text=$(sed 's/<[^>]*>//g' <<< "$text")
    pico2wave -w "$outfile" -l "$lang" "$text"
}

function mycroft() {
    text=$(sed 's/<[^>]*>//g' <<< "$text")
    ."$mycroftPath/mimic" -t "$text" -o "$outfile" -voice "$mycroftPath""/voices/cmu_us_""$voice"".flitevox"
}

if [ "$service" = "google" ]; then
    cache="$cache/google/"
    mkdir -p "$cache"

    text=${text//\'/\\\'}

    languageCode="$lang"-"$country"
    googleVoice="$languageCode"-"$voice"

    md5string="$text"_"$googleVoice"_"$sampleRate"_"$lang"
    hash="$(echo -n "$md5string" | md5sum | sed 's/ .*$//')"

    cachefile="$cache""$hash".wav
    downloadFile="/tmp/""$hash"

    if [[ -f "$cachefile" ]]; then
        cp "$cachefile" "$outfile"
    else
        if [ "$status" != "online" ]; then
            if [[ "$useMycroft" = true ]]; then
                mycroft
            else
                picotts
            fi
        else
            if [ "$text" != *"<speak>"* ]; then
                text="<speak>""$text""</speak>"
            fi

            curl -H "Content-Type: application/json; charset=utf-8" \
            --data "{
              'input':{
                'ssml':'$text'
              },
              'voice':{
                'languageCode':'$languageCode',
                'name':'$googleVoice',
                'ssmlGender':'$gender'
              },
              'audioConfig':{
                'audioEncoding':'MP3',
                'sampleRateHertz':'$sampleRate'
              }
            }" "https://texttospeech.googleapis.com/v1/text:synthesize?key="$googleWavenetAPIKey > "$downloadFile"

            sed -i 's/audioContent//' "$downloadFile" && \
            tr -d '\n ":{}' < "$downloadFile" > "$downloadFile".tmp && \
            base64 "$downloadFile".tmp --decode > "$downloadFile".mp3

            mpg123 --quiet --wav "$cachefile" "$downloadFile".mp3
            rm "$downloadFile" && \
            rm "$downloadFile".tmp && \
            rm "$downloadFile".mp3
            cp "$cachefile" "$outfile"
        fi
    fi
elif [ "$service" = "amazon" ]; then
    cache="$cache/amazon/"
    mkdir -p "$cache"

    amazonVoice=$voice

    md5string="$text""_""$amazonVoice"_"$sampleRate"_"$lang"
    hash="$(echo -n "$md5string" | md5sum | sed 's/ .*$//')"

    cachefile="$cache""$hash".mp3

    if [ -f "$cachefile" ]; then
        mpg123 -q -w $outfile $cachefile
    else
        if [ "$status" != "online" ]; then
            if [[ "$useMycroft" = true ]]; then
                mycroft
            else
                picotts
            fi
        else
            if [ "$text" != *"<speak>"* ];then
                text="<speak>""$text""</speak>"
            fi

            $awscli polly synthesize-speech \
            --output-format mp3 \
            --voice-id "$voice" \
            --sample-rate "$sampleRate" \
            --text-type ssml \
            --text "$text" \
            "$cachefile"

            mpg123 -q -w $outfile $cachefile
        fi
    fi
elif [ "$service" = "picotts" ]; then
    picotts
elif [ "$service" = "mycroft" ]; then
    mycroft
else
    if [[ "$useMycroft" = true ]]; then
        mycroft
    else
        picotts
    fi
fi
	#!/usr/bin/env bash

	# By Psycho
	# Shell script to handle different TTS and online / offline connectivity
	# This bash script can be set as a custom TTS for snips but also called directly from your skills
	# a great way to give more than one personality to your assistant
	# Original script: https://gist.github.com/Psychokiller1888/cf10af3220b5cd6d9c92c709c6af92c2

	####### COMMON #######
	#------------------------------------
	# Set your cache path
	cache="/home/pi/snipsSuperTTS/cache"
	#------------------------------------
	# - Install mpg123
	# - The cache path is created by the script itself at first run! If you already have the cache directories, make sure to set its owner to "_snips" => sudo chown _snips /home/pi/snipsSuperTTS/cache
	# - Edit /etc/snips.toml
	# - Set "customtts" as snips-tts provider
	# - Add as customtts: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "google", "%%LANG%%", "US", "Wavenet-C", "FEMALE", "%%TEXT%%", "22050"]
	# Change "US" to another language country code, "GB" per exemple for a british voice
	# You can customize the "Wavenet-C" to another voice of your choice. https://cloud.google.com/text-to-speech/docs/voices / https://docs.aws.amazon.com/polly/latest/dg/voicelist.html
	# Offline voices possibilities are: picotts or mycroft
	# Fit "FEMALE" to the voice gender you want. Note this is linked to google voices
	# You can change the sample rate, the last argument, to your needs
	# Restart snips: systemctl restart snips-*
	# If you want a total customized experience, you can easily enable both google and amazon and use a different one depending on what you want. Don't be shy, there's no limit
	# Note that not all parameters do something depending on the voice you choose. Those are marked with "--" in the provided examples

	####### MycroftAI - Mimic #######
	# https://github.com/MycroftAI/mimic
	# This one is pretty long to install, but hey, the quality compared to pico is worth it!
	# Set the following option to True to use Mycroft instead of pico. Don't forget to set the path too
	#
	# Example: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "mycroft", "%%LANG%%", "--", "slt_hts", "--", "%%TEXT%%", "22050"]
	#
	# Available voices: aew ahw aup awb axb bdl clb eey fem gka jmk ksp ljm rms rxr slt slt_hts
	# Or you can use an external voice on http.
	#
	# sudo apt-get install gcc make pkg-config automake libtool libasound2-dev
	# git clone https://github.com/MycroftAI/mimic.git
	# cd mimic
	# ./dependencies.sh --prefix="/usr/local"
	# ./autogen.sh
	# ./configure --prefix="/usr/local"
	# make
	# sudo /sbin/ldconfig
	# make check
	useMycroft=false
	mycroftPath="/home/pi/mimic"


	####### GOOGLE #######
	# Install Google SDK: https://cloud.google.com/text-to-speech/docs/quickstart-protocol
	# Follow point 6. to initialize the sdk after creating your service account
	# Get your api key from the console https://console.developers.google.com
	# Uncomment the following and set it accordingly:
	#
	#googleWavenetAPIKey=""
	#
	# Example: command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "google", "%%LANG%%", "US", "Wavenet-C", "FEMALE", "%%TEXT%%", "22050"]

	###### AMAZON #######
	# Install Amazon sdk
	# curl "https://s3.amazonaws.com/aws-cli/awscli-bundle.zip" -o "awscli-bundle.zip"
	# unzip awscli-bundle.zip
	# ./awscli-bundle/install -i /usr/local/aws -b /usr/local/bin/aws
	# Uncomment the following lines and set them accordingly:
	#
	#export AWS_ACCESS_KEY_ID=""
	#export AWS_SECRET_ACCESS_KEY=""
	#export AWS_DEFAULT_REGION="eu-central-1"
	#awscli='/usr/local/bin/aws'
	#
	# command = ["/home/pi/snipsSuperTTS/snipsSuperTTS.sh", "%%OUTPUT_FILE%%", "amazon", "%%LANG%%", "US", "Joanna", "--", "%%TEXT%%", "22050"]
	#
	####################################################################################################

	outfile="$1"
	service="$2"
	lang="$3"
	country="$4"
	voice="$5"
	gender="$6"
	text="$7"
	sampleRate="$8"

	if [ "$service" = "mycroft" ] \|\| [ "$service" = "picotts" ]; then
	status="offline"
	else
	echo -e "GET http://google.com HTTP/1.0\n\n" \| nc google.com 80 > /dev/null 2>&1
	if [ $? -eq 0 ]; then
	status="online"
	else
	status="offline"
	fi
	# Alternative for some people having problem pinging google.com. Comment the above and uncomment the following
	#wget -q --tries=1 --timeout=1 --spider http://google.com
	#if [[ $? -eq 0 ]]; then
	# status="online"
	#else
	# status="offline"
	#fi
	fi

	function picotts() {
	case "$lang" in
	en)
	lang="en-US";;
	de)
	lang="de-DE";;
	es)
	lang="es-ES";;
	fr)
	lang="fr-FR";;
	it)
	lang="it-IT";;
	*)
	lang="en-US";;
	esac
	text=$(sed 's/<[^>]*>//g' <<< "$text")
	pico2wave -w "$outfile" -l "$lang" "$text"
	}

	function mycroft() {
	text=$(sed 's/<[^>]*>//g' <<< "$text")
	."$mycroftPath/mimic" -t "$text" -o "$outfile" -voice "$mycroftPath""/voices/cmu_us_""$voice"".flitevox"
	}

	if [ "$service" = "google" ]; then
	cache="$cache/google/"
	mkdir -p "$cache"

	text=${text//\'/\\\'}

	languageCode="$lang"-"$country"
	googleVoice="$languageCode"-"$voice"

	md5string="$text"_"$googleVoice"_"$sampleRate"_"$lang"
	hash="$(echo -n "$md5string" \| md5sum \| sed 's/ .*$//')"

	cachefile="$cache""$hash".wav
	downloadFile="/tmp/""$hash"

	if [[ -f "$cachefile" ]]; then
	cp "$cachefile" "$outfile"
	else
	if [ "$status" != "online" ]; then
	if [[ "$useMycroft" = true ]]; then
	mycroft
	else
	picotts
	fi
	else
	if [ "$text" != "<speak>" ]; then
	text="<speak>""$text""</speak>"
	fi

	curl -H "Content-Type: application/json; charset=utf-8" \
	--data "{
	'input':{
	'ssml':'$text'
	},
	'voice':{
	'languageCode':'$languageCode',
	'name':'$googleVoice',
	'ssmlGender':'$gender'
	},
	'audioConfig':{
	'audioEncoding':'MP3',
	'sampleRateHertz':'$sampleRate'
	}
	}" "https://texttospeech.googleapis.com/v1/text:synthesize?key="$googleWavenetAPIKey > "$downloadFile"

	sed -i 's/audioContent//' "$downloadFile" && \
	tr -d '\n ":{}' < "$downloadFile" > "$downloadFile".tmp && \
	base64 "$downloadFile".tmp --decode > "$downloadFile".mp3

	mpg123 --quiet --wav "$cachefile" "$downloadFile".mp3
	rm "$downloadFile" && \
	rm "$downloadFile".tmp && \
	rm "$downloadFile".mp3
	cp "$cachefile" "$outfile"
	fi
	fi
	elif [ "$service" = "amazon" ]; then
	cache="$cache/amazon/"
	mkdir -p "$cache"

	amazonVoice=$voice

	md5string="$text""_""$amazonVoice"_"$sampleRate"_"$lang"
	hash="$(echo -n "$md5string" \| md5sum \| sed 's/ .*$//')"

	cachefile="$cache""$hash".mp3

	if [ -f "$cachefile" ]; then
	mpg123 -q -w $outfile $cachefile
	else
	if [ "$status" != "online" ]; then
	if [[ "$useMycroft" = true ]]; then
	mycroft
	else
	picotts
	fi
	else
	if [ "$text" != "<speak>" ];then
	text="<speak>""$text""</speak>"
	fi

	$awscli polly synthesize-speech \
	--output-format mp3 \
	--voice-id "$voice" \
	--sample-rate "$sampleRate" \
	--text-type ssml \
	--text "$text" \
	"$cachefile"

	mpg123 -q -w $outfile $cachefile
	fi
	fi
	elif [ "$service" = "picotts" ]; then
	picotts
	elif [ "$service" = "mycroft" ]; then
	mycroft
	else
	if [[ "$useMycroft" = true ]]; then
	mycroft
	else
	picotts
	fi
	fi