Lip-sync Software Update -- 2

I'm interested in enlisting the services of a programmer to update some open source lip-syncing software: [login to view URL] Currently, users import a sound file into Papagayo and manually type in text to align with the waveform (see [login to view URL]). Based on the words typed, Papagayo then applies phonetic mouth shapes across the sound file. The user can drag words around to align with audio, matching the text with the actual sound file. The user can also right click on a word to further define the correct mouth shapes (see figure [login to view URL]). Once completed, this information is then exported as a .DAT file and imported into various animation applications (primarily Moho 12 or Moho 13 [login to view URL]). Assuming the user has set up a character with the correct corresponding mouth shapes (see [login to view URL]), the user imports the .DAT file and these mouth shapes are applied as keyframes on the timeline. Although the program functions "okay," I would like to see it updated with voice recognition capabilities, so that the user can first run a voice recognition pass and have that text applied to the correct point on the sound file. Afterwards, the user can then further refine the alignment by dragging the words around over the waveform, or right clicking and defining the correct mouth shape. On top of the addition of voice recognition capabilities, I would also like to add some UI improvements. I would also be interested to hear from interested developers if it would be at all possible to incorporate audio recording and editing capabilities (perhaps drawing from other open source audio editors such as Audacity), allowing users to record, edit, and output lip-sync .DAT files all in one application. Initially, I would only be interested in developing a Windows / English version. Thanks!