I want to create an app that can:
1) Record the incoming audio to a file *in addition* to having it converted to text via the google SR server (using the new SpeechRecognizer API).
2) Perform a Speech-to-text function (also using the new SpeechRecognizer API) within my app without displaying the default "Speak Now" dialog.
3) Read/Load-in an already existing recorded voice sound file and pass (stream) it's audio to the google SR server (using the new SpeechRecognizer API) so it will return ASCII text of the spoken words in the previously recorded voice file.
4) Ability to immediately invoke the SR conversion function before a period of silence is detected. In other words, I would like to allow the user to press a "Done" button that will immediately tell the remote google SR server to start the conversion process, instead of waiting for 1-2 seconds of silence after the user stops speaking before the conversion process will start.
So I need a new Library (or Set-of-Routines, object, ect) that I can use from within my app to perform the above functionality.
Here is a link to the new API:
http://developer.android.com/reference/android/speech/SpeechRecognizer.html
Any interested programmers, please PM me with an estimated time and cost to produce a library/routine to do this.
Thank you!
-John
1) Record the incoming audio to a file *in addition* to having it converted to text via the google SR server (using the new SpeechRecognizer API).
2) Perform a Speech-to-text function (also using the new SpeechRecognizer API) within my app without displaying the default "Speak Now" dialog.
3) Read/Load-in an already existing recorded voice sound file and pass (stream) it's audio to the google SR server (using the new SpeechRecognizer API) so it will return ASCII text of the spoken words in the previously recorded voice file.
4) Ability to immediately invoke the SR conversion function before a period of silence is detected. In other words, I would like to allow the user to press a "Done" button that will immediately tell the remote google SR server to start the conversion process, instead of waiting for 1-2 seconds of silence after the user stops speaking before the conversion process will start.
So I need a new Library (or Set-of-Routines, object, ect) that I can use from within my app to perform the above functionality.
Here is a link to the new API:
http://developer.android.com/reference/android/speech/SpeechRecognizer.html
Any interested programmers, please PM me with an estimated time and cost to produce a library/routine to do this.
Thank you!
-John
Last edited: