Realtime Speech Synthesis for Games

I was browsing around Develop and saw an interview with the CEO of Phoenetic Arts. While not holy-grail worthy yet, I can definitely see the productivity boost that their tech will allow. They can basically generate a statistical model of a human voice based on about a 3-hour sample of dialog. From there, it can essentially do text-to-speech of that sounds decent or very high-quality joining between pre-existing audio waveforms. In any event, I’m looking forward to seeing this at GDC this year.

Develop Interview: PA Studio


~ by shaunkime on February 3, 2010.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: