Method and system for collecting audio prompts in a dymanically generated voice application

Abstract

A prompt collecting tool ( 190 ) for an interactive voice response system ( 100 ) includes a voice enabled application server ( 150 ), a voice simulator coupled to the voice enabled application server, and a processor coupled to the voice simulator. The processor can be programmed to execute ( 202 ) a voice application having a plurality of audio prompts, play ( 206 ) audio if a pre-stored audio is available for a particular prompt, capture ( 208 ) text when no pre-stored audio is available and forward ( 210 ) the captured text to the prompt collecting tool. The voice simulator can include a VoiceXML browser ( 160 ), a text to speech text service ( 170 ), and a text based recognition service ( 180 ) for example.

1 . A method of collecting audio prompts in a dynamically generated voice application, comprising the steps of:
 executing a voice application having a plurality of audio prompts;   playing audio if a pre-stored audio is available for a particular prompt;   capturing text when no pre-stored audio is available; and   forwarding the captured text to a prompt collecting tool.   
     
     
         2 . The method of  claim 1 , wherein the prompts are recorded and deployed. 
     
     
         3 . The method of  claim 1 , wherein the method further comprises the step of generating audio from a text-to-speech engine 
     
     
         4 . The method of  claim 1 , wherein the method further comprises the step of repeating the aforementioned steps for every path in the voice application. 
     
     
         5 . The method of  claim 1 , wherein the method further comprises the step of identifying all the paths in the voice application using a call flow builder. 
     
     
         6 . The method of  claim 1 , wherein the method further comprises the step of running a VoiceXML Simulator on the voice application with a browser interpreting VoiceXML. 
     
     
         7 . The method of  claim 6 , wherein the method further comprises the step of delegating text-to-speech service to a text-to-speech text platform and Voice recognition to a text recognition platform. 
     
     
         8 . The method of  claim 7 , wherein the method further comprises the step of capturing and pushing Speech Synthesis Markup Language text to the prompt collecting tool. 
     
     
         9 . A prompt collecting tool for an interactive voice response system, comprising:
 a voice enabled application server;   a voice simulator coupled to the voice enabled application server; and   a processor coupled to the voice simulator, wherein the processor is programmed to:   execute a voice application having a plurality of audio prompts;   play audio if a pre-stored audio is available for a particular prompt;   capture text when no pre-stored audio is available; and   forward the captured text to a prompt collecting tool.   
     
     
         10 . The prompt collecting tool of  claim 9 , wherein the voice enabled application service comprises among a web server, a telephone server, a dialogue server, and a voice server. 
     
     
         11 . The prompt collecting tool of  claim 9 , wherein the voice simulator comprises a VoiceXML browser, a text to speech text service, and a text based recognition service. 
     
     
         12 . The prompt collecting tool of  claim 9 , wherein the processor is further programmed to generate audio from a text-to-speech engine 
     
     
         13 . The prompt collecting tool of  claim 9 , wherein the processor is further programmed to identify all the paths in a voice application using a call flow builder. 
     
     
         14 . The prompt collecting tool of  claim 9 , wherein the processor is further programmed to run a VoiceXML Simulator for a voice application with a browser interpreting VoiceXML. 
     
     
         15 . The prompt collecting tool of  claim 14 , wherein the processor is further programmed to delegate text-to-speech service to a text-to-speech text platform and text recognition to a text recognition platform and further programmed to capture and push Speech Synthesis Markup Language text to the prompt collecting tool. 
     
     
         16 . A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:
 executing a voice application having a plurality of audio prompts;   playing audio if a pre-stored audio is available for a particular prompt;   capturing text when no pre-stored audio is available; and   forwarding the captured text to a prompt collecting tool.   
     
     
         17 . The machine readable storage of  claim 16 , wherein the computer program further comprises a plurality of code sections for causing the machine to generate audio from a text-to-speech engine if text is already associated with the particular prompt.