Speech-to-Text Conversion App for Photos

I need to develop an application to convert speech-to-text for photos taken from a digital camera. When users take a photo, they are able to make a voice recording to go along with the photo, both which are saved to the camera’s SD card (ie. [login to view URL] and [login to view URL]) The app will function as follows: 1. After install, user must register a username 2. App displays photos taken from the camera 3. User chooses to convert voice recordings 4. Data is sent to Speech Recognition server and converted 5. Converted text is sent back and the user can go through and fix incorrect text 6. Once complete, the text is appended to the EXIF data of the JPEG and saved We plan to use Microsoft Speech Recognition or Sphinx-4 for the conversion. We also want to eventually build a website which will take care of points 5 and 6 and also allow the user to send the image to Picasa/Flickr/Facebook etc.