~/bin $ ./mee42_v0.3.1.sh
-----------------------------------------------------------------------------
Mee42 is a shell script which records your voice and tries to answer your
question using Google Voice API for speech recognition, answers.com for db of
answers and espeak for speech synthesis. CopyStraightForward blueslee@tmo.

Recording sound input.................
Speech2txt via Google Voice...........who is Michael Jordan
Getting answer from answers.com.......He is a famous basketball player from the NBA (NationalBasketball Association). He is known for his glory days with the Chicago Bulls.
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........the capital of Tonga
Getting answer from answers.com.......Nuku'alofa is the capital of Tonga. .
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........what is the biggest prime number
Getting answer from answers.com.......There is no biggest prime number. The largest prime known at present is 243112609 - 1, a number with nearly 13 million decimal digits.
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........what is the best smartphone
Getting answer from answers.com.......Iphone_and_Blackberry:D
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........#### you
Getting answer from answers.com.......Something went wrong.
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........what is 42
Getting answer from answers.com.......42 is the answer to life, the universe, and everything. (From the book Hitch hikers guide to the galaxy.) EDIT: aww you beat me to it...
Txt2speech via espeak.................

Recording sound input.................
Speech2txt via Google Voice...........exit

#!/bin/sh
#
# Mee42 - Siri/Google Now for the poor man ;-)  
#
# CopyStraightForward blueslee@tmo
#
# What you need: gst-launch or alternatively arecord + flac, wget, espeak

# Choose your language here, only English is supported yet  
# (html structure of answers from *.answers.com are different)
lang="en"
if [ "${lang}" = 'en' ]; then 
   lang_flag='wiki'
else 
   lang_flag=${lang}
fi

# Maximum speech recording time in sec
speech_rec_time=4  					#use for arecord
speech_num_buffers="$(( 50 * ${speech_rec_time} ))"  	#used for gstreamer 

# Default sample rate for flac. Use 48000 if you are using arecord + flac 
# as flac's --sample-rate=16000 does not work for me  
sample_rate=16000

# Just a shortcut for Google's Voice API Url
api_url='http://www.google.com/speech-api/v1/recognize?lang=${lang}-${lang}\
         &client=chromium'

# Temporary files are named as below with the corresponding suffix
file_prefix='file_temp'
rm -f ${file_prefix}* 


about()
{
cat << EOF
-----------------------------------------------------------------------------
Mee42 is a shell script which records your voice and tries to answer your 
question using Google Voice API for speech recognition, answers.com for db of 
answers and espeak for speech synthesis. CopyStraightForward blueslee@tmo.

EOF
}


# Record voice via gst-launch, alternatively you can use arecord and flac
record_voice()
{
    gst-launch-0.10 pulsesrc num-buffers=${speech_num_buffers} ! audioconvert\
     ! audioresample ! audiorate ! audio/x-raw-int,rate=${sample_rate} ! flacenc\
     ! filesink location=${file_prefix}.flac 1>/dev/null 2>&1

    #arecord -f dat -d ${speech_rec_time} ${file_prefix}.wav 1>/dev/null 2>&1
    #flac --compression-level-5 ${file_prefix}.wav 1>/dev/null 2>&1
    #Remark: sox on N900 doesnt work as below i.e. has no flac support 
    #sox ${file_prefix}.wav ${file_prefix}.flac rate 16k gain -n -5 silence 1 5 2%
}


# Speech2Txt uses Google Voice API
speech2txt()
{
    wget -q -U "Mozilla/5.0" --post-file ${file_prefix}.flac\
     --header="Content-Type: audio/x-flac; rate=${sample_rate}" -O\
     - ${api_url} > ${file_prefix}.ret
    cat ${file_prefix}.ret | sed 's/.*utterance":"//'\
        | sed 's/","confidence.*//' > ${file_prefix}.txt
}


# Get answer from answers.com
get_answer()
{
    # We are replacing ' ' by '_' as a typical request is handled in the http 
    # header, for instance http://wiki.answers.com/Q/who_is_michael_jordan
    sed -e 's/ /_/g' ${file_prefix}.txt > ${file_prefix}2.txt

    request_url="http://${lang_flag}.answers.com/Q/"`cat ${file_prefix}2.txt`
    wget ${request_url} --output-document=${file_prefix}.html 1>/dev/null 2>&1
   
    # The first occurance of 'description' contains our answer
    grep 'og:description' ${file_prefix}.html | head -1\
        | sed -e 's/.*og:description//' | cut -d"\"" -f3,3 > ${file_prefix}.txt
}


# Sanity check if something went wrong, i.e. we have no or wrong answer
error_handling()
{
    errorcheck=`cat ${file_prefix}.txt | cut -c1-4`
    if [ "${errorcheck}" = "http" -o "${errorcheck}" = "" ]; then
       echo 'Something went wrong.' > ${file_prefix}.txt
    fi
}


# Txt2speech via espeak
txt2speech()
{
    espeak -v${lang} -f ${file_prefix}.txt 1>/dev/null 2>&1
}


# Cleanup of temporary files
cleanup()
{
    rm -f ${file_prefix}* 
}


clear
about

while true; 
do 	
    espeak -v${lang} "Ask your question or say exit." 1>/dev/null 2>&1
    printf 'Recording sound input.................'
    record_voice
    espeak -v${lang} "Thank you." 1>/dev/null 2>&1
    sleep 1
    echo

    printf 'Speech2txt via Google Voice...........'
    speech2txt; cat ${file_prefix}.txt

    # Leave the while loop if users says 'exit' || 'quit' || 'stop'
    exit_code=`cat ${file_prefix}.txt`
    if [ "${exit_code}" = "exit" -o "${exit_code}" = "quit"\
                                 -o "${exit_code}" = "stop" ]; then
        cleanup
        exit 0
    fi

    
    printf 'Getting answer from answers.com.......'   
    get_answer
    error_handling 
    cat ${file_prefix}.txt

    printf 'Txt2speech via espeak.................' 
    txt2speech
    echo; echo
   
    cleanup
done