when it is gone. he had to have his vocal track removed, so before that happened we recorded him extensively and we were able to recreate his voice in a speech synthesis system so that he can now type in text and it will speak exactly the way that he spoke. text—to—speech technology has been around for a while. all remember microsoft sam, right? peter provided far more than the average voice sample recording. 15 hours' worth of material. in order to make a voice you take the audio and you use a system to learn how the sounds in the voice relate to the words that are being spoken. once you have that model built you can put a new set of words in and it will produce a new output with that voice. to convey sentiment for specific scenarios, peter captured himself speaking in four different styles. the tone of voice is very important.