Need to define a common folder name where the cached .mp3 files are stored on the server.
A new RESTful api call will be defined in python to simply find a named mp3 file in the folder and return it, instead of calling the tts translation.
All the lines of AI dialog will need to be enumerated with a unique filename.
When the AI chat is sent to the c# cognition class, the filename will need to be passed in with the chat text so we know which line of dialog to retrieve from the cache folder on the server.
Bonus points: Define phonetic info to accompany the data. I believe vocalware supports us giving phonetic hints as to how to properly speak the line so it says "LEED" instead of "LEAD" for example.
Some thoughts on how to do this:
Need to define a common folder name where the cached .mp3 files are stored on the server.
A new RESTful api call will be defined in python to simply find a named mp3 file in the folder and return it, instead of calling the tts translation.
All the lines of AI dialog will need to be enumerated with a unique filename.
When the AI chat is sent to the c# cognition class, the filename will need to be passed in with the chat text so we know which line of dialog to retrieve from the cache folder on the server.
Bonus points: Define phonetic info to accompany the data. I believe vocalware supports us giving phonetic hints as to how to properly speak the line so it says "LEED" instead of "LEAD" for example.