You may want to look up what was done for Roger Ebert. He has lost his voice due to surgery, but because of the vast corpus of audio recordings of him, a viable text to speech engine was able to be created.
It’s a bit dated at this point, but I imagine the research has vastly improved since then.
It’s a very good question though. A decade ago this was able to be done for one man. Is it now possible to be done for anyone? Like others, I’d guess the first step is to record everything while you can.
It’s a bit dated at this point, but I imagine the research has vastly improved since then.
It’s a very good question though. A decade ago this was able to be done for one man. Is it now possible to be done for anyone? Like others, I’d guess the first step is to record everything while you can.