============================================== iSpeech plugins for Asterisk ============================================== These plugins provide access to iSpeech Text To Speech and Automatic Speech Recognition services making them available for use with Asterisk PBX. http://www.ispeech.org/ ------------ Requirements ------------ Perl The Perl Programming Language libwww-perl The World-Wide Web library for Perl (LWP) IO::Socket::SSL Perl module that implements an interface to SSL sockets. URI::Escape Perl module for "URI escaping". format_mp3 Asterisk mp3 format support. An API key from iSpeech: To obtain an API key please visit: http://www.ispeech.org/developers and register for a developer account. Internet access in order to contact iSpeech and get the speech and text data. ** Optional** speex patent-free audio compression format designed for speech. ------------ Installation ------------ To install copy ispeech-asr.agi and ispeech-tts.agi to your agi-bin directory. Usually this is /var/lib/asterisk/agi-bin/ To make sure check your /etc/asterisk/asterisk.conf file ----- Usage ----- agi(ispeech-tts.agi,"text",[voice],[intkey],[speed]): This will invoke the iSpeech TTS engine, render the text string to speech and play it back to the user. If 'intkey' is set the script will wait for user input. Any given interrupt keys will cause the playback to immediately terminate and the dialplan to proceed to the matching extension (this is mainly for use in IVR, see README for examples). If 'speed' is set the speech rate is altered by that factor. agi(ispeech-asr.agi,[lang],[freeform],[model],[timeout],[intkey],[NOBEEP]): Records from the current channel untill 3 seconds of silence are detected (this can be set by the user by the 'timeout' argument, -1 for no timeout) or the interrupt key (# by default) is pressed. If NOBEEP is set, no beep sound is played back to the user to indicate the start of the recording. For 'freeform' and 'model' please refer to the ispeech API manual. 'freeform' defaults to 3 (Normal speech) The recorded sound is send over to iSpeech ASR service and the returned text string is assigned as the value of the channel variable 'utterance'. The script sets the following channel variables: status : Return status. 0 means success, non zero values indicate different errors. utterance : The generated text string. confidence : A value between 0 and 1 indicating how 'confident' the recognition engine feels about the result. Values bigger than 0.90 usually mean that the resulted text is correct. -------- Examples -------- sample dialplan code for your extensions.conf ;iSpeech TTS test exten => 3,1,Answer() exten => 3,n,agi(ispeech-tts.agi,"This is a test of the ispeech text to speech engine in asterisk.") exten => 3,n,agi(ispeech-tts.agi,"Esta es una simple prueba en español.",usspanishfemale) exten => 3,n,agi(ispeech-tts.agi,"这是一个简单的测试，在中国。有一个愉快的一天。",chchinesefemale) exten => 3,n,Hangup() ;Speech recognition test exten => 4,1,Answer() exten => 4,n,agi(ispeech-tts.agi,"Please say something in English. When done press the pound key.") exten => 4,n(record),agi(ispeech-asr.agi,en-US) exten => 4,n,Noop(== Script returned: ${status} , ${confidence} , ${utterance} ==) exten => 4,n,GotoIf($["${status}" = "0"]?success:fail) exten => 4,n(success),GotoIf($["${confidence}" > "0.3"]?playback:retry) exten => 4,n(retry),agi(ispeech-tts.agi,"Can you please repeat more clearly?") exten => 4,n,goto(record) exten => 4,n(playback),agi(ispeech-tts.agi,"The text you just said was...") exten => 4,n,agi(ispeech-tts.agi,"${utterance}") exten => 4,n,goto(end) exten => 4,n(fail),agi(ispeech-tts.agi,"Failed to get speech data.") exten => 4,n(end),Hangup() ;Voice dialing example exten => 5,1,Answer() exten => 5,n,agi(ispeech-tts.agi,"Please say the number you wish to dial.") exten => 5,n(record),agi(ispeech-asr.agi,en-US,,phonenumber) exten => 5,n,GotoIf($[$["${status}" = "0"] & $["${confidence}" > "0.3"]]?success:retry) exten => 5,(success),agi(ispeech-tts.agi,"Dialing ${utterance}") exten => 5,n,goto(${utterance},1) exten => 5,n(retry),agi(ispeech-tts.agi,"Can you please repeat?") exten => 5,n,goto(record) ;IVR test exten => 6,1,goto(my_ivr,s,1) [my_ivr] exten => s,1,Answer() exten => s,n,Set(TIMEOUT(digit)=5) exten => s,n,Set(TIMEOUT(response)=8) exten => s,n,agi(ispeech-tts.agi,"Welcome to my small interactive voice response menu.") exten => s,n(start),agi(ispeech-tts.agi,"Please dial a digit.",,any) exten => s,n,Waitexten() exten => _X,1,agi(ispeech-tts.agi,"You just pressed ${EXTEN}. Try another one please.",,any) exten => _X,n,Waitexten() exten => i,1,agi(ispeech-tts.agi,"Invalid extension.") exten => i,n,goto(s,start) exten => t,1,agi(ispeech-tts.agi,"Request timed out.") exten => t,n,goto(h,1) ----------------------- TTS Supported Languages ----------------------- Standard Voices Name Alias ================================================= US English Female usenglishfemale (default) US English Male usenglishmale UK English Female ukenglishfemale UK English Male ukenglishmale Australian English Female auenglishfemale US Spanish Female usspanishfemale US Spanish Male usspanishmale Chinese Female chchinesefemale Chinese Male chchinesemale Hong Kong Cantonese Female hkchinesefemale Taiwan Chinese Female twchinesefemale Japanese Female jpjapanesefemale Japanese Male jpjapanesemale Korean Female krkoreanfemale Korean Male krkoreanmale Canadian English Female caenglishfemale Hungarian Female huhungarianfemale Brazilian Portuguese Female brportuguesefemale European Portuguese Female eurportuguesefemale European Portuguese Male eurportuguesemale European Spanish Female eurspanishfemale European Spanish Male eurspanishmale European Catalan Female eurcatalanfemale European Czech Female eurczechfemale European Danish Female eurdanishfemale European Finnish Female eurfinnishfemale European French Female eurfrenchfemale European French Male eurfrenchmale European Norwegian Female eurnorwegianfemale European Dutch Female eurdutchfemale European Polish Female eurpolishfemale European Italian Female euritalianfemale European Turkish Female eurturkishfemale European Turkish Male eurturkishmale European German Female eurgermanfemale European German Male eurgermanmale Russian Female rurussianfemale Russian Male rurussianmale Swedish Female swswedishfemale Canadian French Female cafrenchfemale Canadian French Male cafrenchmale ----------------------- ASR Supported Languages ----------------------- Language Alias ======================================= English (US) en-US (default) English (Canada) en-CA English (UK) en-GB English (Australia) en-AU Spanish (Spain) es-ES Spanish (Mexico) es-MX Italian (Italy) it-IT French (France) fr-FR French (Canada) fr-CA Polish (Poland) pl-PL Portuguese (Portugal) pt-PT Catalan (Catalan) ca-ES Chinese (Taiwan) zh-TW Danish (Denmark) da-DK German (Germany) fr-FR Finnish (Finland) it-IT Japanese (Japan) ja-JP Korean (Korea) ko-KR Dutch (Netherlands) nl-NL Norwegian (Norway) nb-NO Portuguese (Brazil) pt-BR Russian (Russia) ru-RU Swedish (Sweden) sv-SE Chinese (China) zh-CN Chinese (Hong Kong) zh-HK ----------------------- Security Considerations ----------------------- These scripts contact iSpeech servers in order send the recorded voice or text and get back the resulted data. Consider enabling SSL to encrypt all the traffic between your pbx and iSpeech servers so no 3rd party can eavesdrop your communication. To do so please set: my $use_ssl = 1; in to the 'User defined parameters' in each AGI script. ------- License ------- The iSpeech asterisk plugins are distributed under the GNU General Public License v2. See LICENSE for details. -------- Homepage -------- http://zaf.github.io/asterisk-ispeech/