I've been looking at a few text-to-speech programs recently, such as this one. This type of software has seemingly come a long way since the days of Microsoft Sam. I imagine it would prove very useful for sport game commentary, in which case the pitch and tone of the voice could be changed to suit various situations, such as excitement or annoyance for example. It would also significantly eliminate repetitive sport commentary that has been a problem in sports games from the moment commentary was first used in them.
So has text-to-speech synthesis reached a point where it is viable for use in games, i.e. is it natural sounding enough yet? Or does the technology still need more time to mature?
So has text-to-speech synthesis reached a point where it is viable for use in games, i.e. is it natural sounding enough yet? Or does the technology still need more time to mature?