Real-Time Voice Cloning Toolbox

Is there any way to run command to generate voice by command in cloud?

koool

wonder what gpu did you use? its running pretty fast or you make the learning video shot fast?

Is language important there? Can I do it same with Turkish text speech?

：００

I noticed you never explained how to install it tho.

software name

How can you install it like that? Is that an .exe file? Or not?

Hello! whenever I try to import audio file (Urdu language ) in sv2tts so i get this error (can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool).
And I already convert my audio file datatype for float, int, complex but still not working. I am very disappointed. Please help me as soon as possible. @Corentin Jemine

Anyone up here after corqui realtime voice clonning?

this isn't Live Mode right?

Does this work LIVE?

please release win version compilated programm!

amazing, would be cool if you could merge
several voices

Can it make a 30 mins audio?

Try to imagine add this to a generative AI and start making calls to familiars that lost their beloved ones acting as if the person would be alive

There is a standalone version in the form of an installation file, as is done with Stable deffusion, to run the program through an exe shortcut.

the fact that this has already existed 4 years ago

This is so amazing.❤

how to run it ??

Would it be possible to use this for other languages besides English?

after selecting speaker if i click on load button then it shows load() takes 1 positional argument but 2 were given

this is crazy, ill experiment

you need to work on your enunciation. genuinely, the words come falling out your mouth, almost like you just went to the dentist and can't use your mouth properly

can you just please send already done file. Don't be unfair please. I don't have coding abilities to do that. so please don't be indifferent to people who have this disability like me

Anyone who has built pre-trained models using their own voice? We tried and it took days...

how to change singer to another singer without chane lyrics ?

this work on spanish???

Hello friend. I've been using vocoders and graphs but this video really shows me some cool stuff.

Is this software available anywhe?******

You and Ukraine by chance. I escape Kiev before the wall fell. Would love to talk to you about some of the stuff. Especially intrigued about the different vocoders.

Thanks For The Cloned Card My Dogg DAWGGOAT I Almost Went Crazy Cuz Of Yo Card😂 When Atm Approved The Card And Start Throwing Da Amount I Click On Out.. You Just Got Yourself Another Long Term Business Customer

dude wtf am i missing here i followed all you instructions but i cant get the output to come out anywhere near as close as yours was coming in any ideas

do i need those datasets to make my embedding voice sounds great? or maybe i don't?

hey, please help me.
when i run (python demo_toolbox.py) i get the following error:
Arguments:
datasets_root: None
models_dir: saved_models
cpu: False
seed: None

Error in sys.excepthook:

Original exception was:

TupAc voice clone

This doesn't work

The guide on the project no longer works, wish you would have had binaries of this

This Guy doesn't get enough credit. Every implementation of this technology should be paying you 10% at least.

we need kevin conroys batman voice to be clonned

THAT'S IINCREDIBLE!

it is multi-language ?

Can it be used for russian?

How do you bring this UI? I see only code.

Thank you for sharing your project! I was curious if I was able to clone voice speeches of characters of the GTA 5 game this way, so I can TTS output them with my own text. Unfortunately, it isn't suitable for cloning voices from these characters. Although, the recorded audio of the source is very high quality, I think the problem is that the characters do shouting, and are acting too emotionally.

The result sounds very weird, like if someone is getting out of breath, someone is being choked or something haha..

Do you have an idea if there are other projects or maybe at ResembleAI is a feature to upload audio source files and TTS output them? I would like to mainly try it out for speeches of game characters, so speeches are fixed and I cannot let them speak a certain script sentence.

This is great software and thanks for keeping it free. I was searching for voice cloning software to clone my granny's voice(she is not alive) so i can feel her close to me. Thanks again for such a wonderful tool. I will try it.

Let me guess, 3 years later and no progress was made?

the dataset speaker and utterance things are grayed out for me why is that
also it generates quite a different picture while vocoding the thing and the output doesnt really sound like the put in sound
ive synthesized and vocoded a few now and its further away on the thing than a completely different speaker
i guess ive set up something wrong but its not very clear

it is only available to english? or i can use it inPT-BR?