Quote:
Originally Posted by issybird
I've only ever used Alexa and I don't know if virtual voice (or other platforms) do a better job. She's ok. More nuance than you'd expect and pretty good at pronunciation; her worst failing is that she doesn't know the difference between "content" (happy) and "content" (innards). Or "produce" (make) and "produce" (veggies). Or "present" and "present". Etc. It's jarring. And while she's animated, not monotone, she obviously can't do different characterizations. It's all just her. Kind of like a dumb but enthusiastic babysitter.
It's good enough to tide me over with a Kindle book when I want to keep going but have to be hands or eyes or both free, but "free" is the operative word.
|
They all kinda suck that way. I think the newer TTS models that benefit from LLMs giving
some context to what is being read can help so hopefully in a few years it'll be better.