Check out coque-tts. Seems promising.

 

That would be great ;)

 

I have tried. In the web version it freezes at the status "uploading". As program version it shows the error "Converged (lack of improvement in inertia) at step 1152/48215".

 

But of course that would be the opinion of the software's developers.

 

A few years ago, a version Adobe Audition was set to be released with voice-faking capability, but that feature was withheld out of prudence. But look at what we have now.

 

I am t

I am the developer

 

I saw someone troll the server from call of duty
he was using arnold zwarchnegger voice and andrew tate
Is it possible in realtime or how its done?

 

@itisntreal GitHub - voicepaw/so-vits-svc-fork: so-vits-svc fork with realtime support, improved interface and more features.

 

Hi,

anybody here with a similar problem?
I am very excited for curtified's version. ;)

 

New Google Soundstorm will be the best in it

 

Is it available at the moment?

 

I wanted to try it with a preconfigured model of Frank Sinatra. But when I wanted to activate the Realtime Voice Changer as described in the video, the Windows-CMD (I own Windows 10 with an Intel(R) Core(TM) i5-6402P CPU @ 2.80GHz 2.81 GHz/AMD) stayed for hours at the first step. ;( Right here:

 

Last edited: Aug 2, 2023

of course you are

no and will be paid

 

Sorry, I don't quite understand your post. Or are you just kidding? Back to the basic problem: How can this be implemented with the AI voice or what am I doing wrong, since I only get errors despite the instructions?

If someone could help me, it would be great

 

Last edited: Aug 3, 2023

Bumping this thread because as promised, I wanted to share with the AS community the FREE app I've been working on for voice and instrument cloning.

https://www.tryreplay.io/ It runs locally! No server is needed! We even have stem separation, de-reverb built in. We're about to launch a plugin in a few weeks too!

We've also built an AI model hosting platform over at https://www.weights.gg/ (with 75k+ users & 16k+ models). Think of it as a Splice for AI models. Please download or contribute your models to our library!

We're open to feedback from the music-making community, so please share any thoughts here or on our Discord(s).

 

Wow,

thank you very much for the software, but will it also be possible to model models (my favorite speaker as said at the beginning of the thread)?

 

@curtified This is amazing!! Thank you for sharing this with the community!!

 

Thanks a lot!
But...the app tries to connect to the inet upon launch (in order to get default datasets/voices?), which is highly undesirable on offline machines. Therefore my question - could you please provide download links to these default voices to make them accessible from different computer, as well as information where to put them on the target machine once they're downloaded?

 

@curtified

What software is needed to make custom models?