Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by guerrilla on Thursday January 08, 2026 @07:49PM
(#46548712)
I don't understand the comments here at all. I played the audio and it sounds absolutely horrible, far worse than computer voices sounded fifteen years ago. Not even the most feeble minded person would mistake that as a human. Am I not hearing the same thing everyone else is hearing? It sounds straight up corrupted to me. Tested in different browsers, no difference.
[ Parent
| on HN ]
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by sammyyyyyyy on Thursday January 08, 2026 @07:53PM
(#46548743)
As I said, some reference voices can lead to bad voice quality. But if it sounds that bad, it’s probably not it. Would love to dig into it if you want
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by guerrilla on Thursday January 08, 2026 @07:54PM
(#46548757)
I mean I'm talking about the mp4. How could people possibly be worried about scammers after listening to that?
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by sammyyyyyyy on Thursday January 08, 2026 @07:56PM
(#46548769)
I didn’t specially cherry pick those examples. You can try it anyway for yourself. But thanks for the feedback anyway
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by guerrilla on Thursday January 08, 2026 @08:26PM
(#46549019)
No shade on you. It's definitely impressive. I just didn't understand people's reactions.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by jrmg on Friday January 09, 2026 @06:36AM
(#46552782)
It sounds like someone using an electrolarynx to me.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by codefreakxff on Thursday January 08, 2026 @10:33PM
(#46549768)
I agree with the comment above. I have not logged into hacker news in _years_ but did so today just to weigh in here. If people are saying that the audio sounds great, then there is definitely something going on with a subset of users where we are only hearing garbled words with a LOT of distortion. This does not sound like natural speech to met at all. It sounds more like a warped cassette tape. And I do not mean to slight your work at all. I am actually incredibly puzzled here to understand why my perception of this is so radically different from others!
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by guerrilla on Thursday January 08, 2026 @10:48PM
(#46549850)
Thank you for commenting. I wonder if this could be another situation like "the dress" (2015) or maybe something is wrong with our codecs...
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by Mashimo on Friday January 09, 2026 @01:48AM
(#46550798)
No, nothing wrong with your codecs. It's sounds shitty. But given the small size and speed it's still impressive.
It's like saying .kkrieger looks like a bad game, which it does, but then again .kkrieger is only 96kb or whatever.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by guerrilla on Friday January 09, 2026 @02:44AM
(#46551074)
How big are TTS models like this usually?
.kkrieger looks like an amazing game for the mid-90s. It's incomprehensible that it's only 96kb.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by Mashimo on Friday January 09, 2026 @04:28AM
(#46551806)
Here is an overview: https://www.inferless.com/learn/comparing-different-text-to-...
Also keep in mind the processing time. The ^ article above used a NVIDIA L4 with 24-GB VRAM. Sopro claims 7.5 second processing time on CPU for 30 seconds of audio!
If you want to get real good quality TTS, you should check out elevenlabs.io
Different tools for different goals.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by foolserrandboy on Thursday January 08, 2026 @08:25PM
(#46549010)
I thought it was RFK
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by serf on Thursday January 08, 2026 @08:39PM
(#46549102)
spasmodic dysphonia as a service.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by jackyysq on Friday January 09, 2026 @12:06AM
(#46550254)
same here, tried few different voices including my kids and my own, the generated audio is not similar at all, it's not even a proper voice
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by wildmXranat on Friday January 09, 2026 @07:25AM
(#46553151)
Yes, if this selected piece is the best that was available to be used as a showcase, it's immediately off putting in distortion and mangling of pronunciation.
Re:Sopro TTS: A 169M model with zero-shot voice cloning that...
by eigenvalue on Friday January 09, 2026 @09:20AM
(#46554106)
Thank you, I was scrolling and scrolling in utter disbelief. It sounds absolutely dreadful. Would drive me nuts to listen to for more than a minute.