President John F. Kennedy can be heard reading a speech he was set to give on Nov. 22, 1963, thanks to sound engineers painstakingly recreating his voice.
On Friday, Scottish text-to-speech company CereProc released a recording of the speech, made with 116,777 voice samples, each less than half a second long, taken from 831 speeches and radio addresses Kennedy made throughout his life. He was supposed to make the address at the Dallas Trade Mart, which he was on his way to when he was assassinated by Lee Harvey Oswald.
"There are only 40/45 phones in English so once you've got that set you can generate any word in the English language. The problem is that it would not sound natural because one sound merges into the sound next to it so they're not really independent. You really need the sounds in the context of every other sound and that makes the database big," CereProc co-founder and chief voice engineer Chris Pidcock told The Times.
"Because of the old analogue recording devices used, it appeared as if it was a different person speaking each time. Trying to harmonize the environment and manipulate the audio so that it ran together was quite difficult," he added.
Less than half of the samples in the speech, which ran for 20 minutes, were side-by-side in the original recordings they were pulled from.
"Getting to that point is pretty challenging based on the variable audio quality, as well as the speech itself having different qualities and noise levels," Pidcock said. "One of the things we needed to do is get a very accurate transcription of the audio so that things like 'umms' and 'ehs' could be labeled and we could make sure the phonetic pieces we got were correct. If you label them incorrectly you might pick the wrong piece and the whole sentence will sound wrong."
© 2025 Newsmax. All rights reserved.