Re:Prime Voice AI: The most realistic and versatile AI speec...
by godelski on Wednesday February 01, 2023 @03:52AM
(#34608088)
I think their model poorly weights the spatial context in sentences. Humans speak with a little rhythm: cadence. The lack of cadence and emotion puts it in deep in the uncanny valley.
Re:Prime Voice AI: The most realistic and versatile AI speec...
by ilaksh on Wednesday February 01, 2023 @05:14AM
(#34608607)
They have a dial for stability and one for clarity. The stability one in particular when turned up reduces the expressiveness.
Re:Prime Voice AI: The most realistic and versatile AI speec...
by Savaaki on Wednesday February 01, 2023 @04:20AM
(#34608257)
Thats a pretty high bar, have you tried inputting ha ha ha into literally any other TTS engine? It never produces great results.
Re:Prime Voice AI: The most realistic and versatile AI speec...
by x-desire on Wednesday February 01, 2023 @04:22AM
(#34608266)
Yeah, when I tried their demo I was a bit confused too - it's not that impressive.
But their model is really good when it comes to cloning voices from small audio samples. It was discovered by 4chan unfortunately [1]. I have only seen a few clips but all of them were racist, sexist or worse. Not appropriate to link them here, I guess. You can see an official sample on their YouTube channel [2]. However, the voices and conversations I've heard yesterday, other than being disgusting, were high quality, believable and full of emotions. The voices of Obi Wan Kenobi or Joe Biden sounded so genuine that it was creepy. I know there has been tools to deepfake voices for years now, but this is the first time I'm seeing one that sounds so authentic.
[1]: https://www.theverge.com/2023/1/31/23579289/ai-voice-clone-d...
The actual sound quality of the output is impressive (clear treble, no weird artifacts between syllables, etc.), but I just don't understand the weird "edginess" of the speech.