polly.sh

#!/bin/bash

usage() {
    echo "Usage: $0 [-v <Ruth|Matthew|Amy>]" 1>&2
    echo "Ruth : Female English (US) - Default" 1>&2
    echo "Matthew : Male English (US)" 1>&2
    echo "Amy : Female English (British)" 1>&2
    exit
}

while getopts ":v:" OPT; do
    case "${OPT}" in
        v)
            VOICE=${OPTARG}
            [ "${VOICE}" = "Ruth" ] || [ "${VOICE}" = Matthew ] || [ "${VOICE}" = Amy ] || usage
            ;;
        *)
            usage
            ;;
    esac
done
shift $((OPTIND-1))

if [ -z "${VOICE}" ]; then
    VOICE="Ruth"
fi

TMP_TEXT_FILE=$(mktemp)
cat > ${TMP_TEXT_FILE}
cat ${TMP_TEXT_FILE}
TMP_VOICE_FILE=$(mktemp)
echo "Using ${VOICE} voice."
aws polly synthesize-speech --output-format mp3 --region us-east-1 \
    --text "$(cat ${TMP_TEXT_FILE})" \
    --voice-id ${VOICE} --engine generative ${TMP_VOICE_FILE}
afplay ${TMP_VOICE_FILE}
rm ${TMP_TEXT_FILE} ${TMP_VOICE_FILE}