Voice Recognition for the Raspberry Pi (STT)

speech2txt-bing.sh

#!/bin/bash
#  Usage:  ./speech2txt-bing.sh
#  Record and send audio file through Bing speech recognition API.
#
# The original script can be found here:
# https://stackoverflow.com/questions/38139809/408-request-timed-out-microsoft-speech-to-text/41111609#41111609
#
SUBSCRIPTION_KEY=<ENTER_SUBSCRIPTION_KEY>
LOCALE=en-US
SCENARIOS=ulm
SAMPLERATE=8000
CODEC=audio/pcm

TARGET_FILE=/tmp/out.wav
INSTANCE_ID=`uuidgen`    # random GUID for instance
REQUEST_ID=`uuidgen`     # random GUID for request
APPID=D4D52672-91D7-4C74-8AD8-42B1D98141A5   # APPID for Bing Speechrec API, don't change
DEVICE_OS=linux          # arbitraty
FORMAT=json

AUTH_TOKEN=`curl -s -X POST "https://api.cognitive.microsoft.com/sts/v1.0/issueToken" -H "Content-type: application/x-www-form-urlencoded" -H "Content-Length: 0" -H "Ocp-Apim-Subscription-Key: ${SUBSCRIPTION_KEY}"`

clear
echo "###############################"
echo "# Recording for 15 seconds... #" # 15 Seconds maximum
echo "###############################"
arecord -f dat -d 5 -D plughw:CARD=Webcam,DEV=0 $TARGET_FILE

clear
echo "###############"
echo "# You said... #"
echo "###############"
echo `curl -s -X POST "https://speech.platform.bing.com/recognize?scenarios=${SCENARIOS}&appid=${APPID}&locale=${LOCALE}&device.os=${DEVICE_OS}&version=3.0&format=${FORMAT}&instanceid=${INSTANCE_ID}&requestid=${REQUEST_ID}" -H "Authorization: Bearer ${AUTH_TOKEN}" -H "Content-type: audio/wav; codec='${CODEC}'; samplerate=${SAMPLERATE}" --data-binary @${TARGET_FILE} | cut -d"\"" -f18`