[jalada]

I know there's a lot of concerns about generative voices, but it's a shame the only solution is 'insist on a live recording of random phrases'. For those whose voices have already degenerated, but who have hours of recordings available from historical sources (e.g. speech therapy sessions), it's too late to ask them to record something fresh.

Don't get me wrong, it's fantastic to see the tech being used this way. My Dad has lost most of his speech due to some kind of aphasia-causing condition and if this had been available just a year or two ago it could've been a big help for him; it's reassuring that others earlier in the journey will benefit from this.

[elicash]

It's not necessarily the only solution, just the one Apple has started with. My guess is that at least in part there are technical reasons, since even this structured approach will require overnight processing (source: WaPo) by Apple.

I do think additionally, in the case for a situation like with your dad, Apple would need to verify that he is the same person that there's hours of audio of. That strikes me as a difficult at Apple's scale.

[nier]

Archive link for mentioned Washington Post article: https://archive.is/CPk7H

[comex]

Note that article says the overnight processing is done by the device, not by Apple itself.

[desro]

You may want to check out Rhasspy/Piper [0,1]. The Piper page includes training instructions.

[0] https://github.com/rhasspy

[1] https://github.com/rhasspy/piper