You need to do voice banking. It is imperative that you do so, so that your wife keeps her identity no matter what.
What you need to do is spend the entire next 3 weeks doing voice banking. This will give your wife a text-to-speech voice (SAPI 5 voice, or others, for example). You record phrases that the voice banking service wants you to speak, with a high quality headset (best if wired) in a quiet setting.
The more sentences (samples) you have, the better the voice will be, obviously. But, there are services out there that will update the recordings, as the technology gets better, and that is the way to go, in terms of choosing the "best service".
I would say that Acapela my-own-voice is currently the best technology. Obviously there are open source technologies, but you do not have the luxury of time to figure all of that out. However, you should do your own voice banking for later post-processing on your own with open source stuff.
There is also a free version of voice banking available, but I would only recommend it as a secondary tool: https://www.modeltalker.org/
This app (iOS and Android) for example, allows you to use your personal voice banked text-to-speech voice, to talk: https://therapy-box.co.uk/predictable
What you need to do is spend the entire next 3 weeks doing voice banking. This will give your wife a text-to-speech voice (SAPI 5 voice, or others, for example). You record phrases that the voice banking service wants you to speak, with a high quality headset (best if wired) in a quiet setting.
The more sentences (samples) you have, the better the voice will be, obviously. But, there are services out there that will update the recordings, as the technology gets better, and that is the way to go, in terms of choosing the "best service".
The voice banking services that people typically use are here: https://www.mndassociation.org/professionals/management-of-m...
I would say that Acapela my-own-voice is currently the best technology. Obviously there are open source technologies, but you do not have the luxury of time to figure all of that out. However, you should do your own voice banking for later post-processing on your own with open source stuff.
There is also a free version of voice banking available, but I would only recommend it as a secondary tool: https://www.modeltalker.org/
This app (iOS and Android) for example, allows you to use your personal voice banked text-to-speech voice, to talk: https://therapy-box.co.uk/predictable
This is another great app that allows you to use your personal voice banked text-to-speech voice: https://www.assistiveware.com/products/proloquo4text
Source: Disabled engineering student, who is extremely interested in assistive technology. I would love to be a rehabilitation engineer.