Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Cool, but I'm sure there must be some better link for this material. Quote from a YouTube comment: Now if we could only get text to speech from "OK" to "blows you away", instead of "your drunk uncle talking from down an empty well"



https://beta.elevenlabs.io/

I've been playing with TorToiSe and other emerging local projects with voice cloning, but ElevenLabs is so far ahead that it's the only one I've considered promoting to clients.


Wow!


I thougt AI today could do better than this. Sounds like 80s speech synth. Even Dr Sbaitso was better.


I'm going to have to defer to Louis CK on that one

https://www.youtube.com/watch?v=PdFB7q89_3U


It’s hilarious, but in this case I think it doesn’t apply. There is next to zero content here that is actually contributed by the person who made the video, and the voice over is pretty horrible. But it did get to front page so maybe I’m just wrong!


Okay. Then I think I see where you're coming from.

From my perspective this was the mainly the first contact with the research presentation and the renderings, and I think those are undeniably very impressive to most people at this point in time.

But viewing it as a "Youtube value-add", or whatever the jargon for that phenomenon might be, I guess it's close at hand to judge it as poor, lazy work that doesn't do the original material justice.

I will also admit it is something of a funny juxtaposition to have the photorealistic, high-definition graphics along with voiceover that is very obviously artificial.


It's a funny bit, but this particular voice over is awful. Simply terrible, F- quality. There are 10 other links intthis thread that would have produced a better voice, or the publisher could have just read the material themselves.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: