With all the neat AI stuff these days, is there a service that takes a person's voice and turns it into a SAPI5 synthesizer? I know companies like LyreBird are working on the voice part, but they never let you use the generated voice outside of their website.
@alexhall @queenslight@pone.social RH Voice is not AI-based but if you can set up it right, it is possible to train a model on a bunch of recordings associated with sentences of prepared script and generate anything RH Voice works on: SAPI 5, NVDA Addons, Android APK's, Linux packages etc. I'm sort of surprised this hasn't caught on more in the community. I'll try to dig up a tutorial someone in Poland wrote on how to set up things properly for it to work.
@Piciok @queenslight [pone.social] Really? That's neat. I tried RHVoice, and it wasn't bad. I didn't know it could be trained.
@pvagner @Piciok @queenslight [pone.social] Ah, thank you. This looks extremely involved. Wow.
@miki @pvagner @Piciok @queenslight [pone.social] I'm not sure what that is, but if it makes the process easier, I'll just wait for that.
@alexhall @pvagner @Piciok @queenslight@pone.social It’s a Google run service for training AI models and playing with all kinds of machine learning algorithm, free as long as you don’t overuse it. It’s based on Jupyter, but as far as I’ve heard, the fork they’re running is more accessible than the open source version.