This takes AI generated voices to a whole new level.

PlayHT introduces PlayHT2.0, a conversational Text-to-Voice AI model that's trained and built to generate humanlike conversations across languages with <1s latency:

People keep telling me that the AI voices don't sound real and won't convey emotions. We are at the very beginning of all of this we can already choose not only the emotional tone but the langauges we want to hear that emotional tone in.

@olucurious

Funny how the german text is wrong but the voice is translated correctly xD I think if you listen closely you still hear it, but if you don't expect it it's insanely good. Looking forward to have this on any YT video so you can watch all languages in your own

@MikePFrank The Japanese vocal clip audio doesn't match the text shown in the video. 🤷‍♂️

😲😲😲

@shipin_xiazai

Wowza!! 🙌

i dont know how i feel about this like it sound too real i really wont be able to trust any audio i hear kinda real

😃😃