How good would it sound if the tts (is it tortoise?) voice model would also be of the exact person you want to impersonate and then be send through the rvc part?
hey troublechute, i have a really imp Q and pls replsy asap. so last year when we had the colab training model, i used multiple colabs to train voice models all days and nights in colab . each of those contained .pth file and .json files. but now idk weirdly, these new suff are asking for .indx files ??? so how can i turn my .json files into .index files. pls help with this. do i have to train again or what. i dont uinderstand. i havent seen the format of the .index files so am not relaly sure how i can acheive this.
i hope is not too late but i have a question, does this work for a virtual cable? or is there a way to use it so when the ai voice sounds the people on the other side of a video call on discord would hear it?
This could be so good, but the base TTS Models are so bad and robotic sounding, and it carries through into the final conversion no matter how well your model is trained. Is there anywhere to get better base TTS Models?? Thanks for the video
Getting constant failures building the wheel file for lxml in the windows install bat file. I've tested Python 3.9.10, 3.9.13 (the one you list), 3.10.0 and 3.11, as well as a vcpkg install. End result is a "ModuleNotFoundError: No module named 'tensorboard'" when running go-applio.bat Manually installing tensorboard via conda also doesn't resolve it.
Hello, let's say i want to generate a Text to Speech with a rvc model but I want the speech to be generated following a certain type of accent, emotion and tone, perhaps inserting an audio as a model to instruct the AI to generate the speech with the same tone, accent and emotions as the audio example, how can I do this? it's possible? or to do something like this am I forced to record an audio with my voice and generate it directly from my recorded audio? Thank you in advance guys, wish you the best and a happy new year!
Thank you for such a wonderful tutorial! 💙💙 Can you please explain how to DELETE a model? After importing SAME models with different versions for testing which is the best, the DROP DOWN LIST became huge. EDIT: In case anyone want to know, I found out it's under /logs/weight Also, is there a way to control the TTS emotion or the "way" things are saying? such as SAD, HAPPY, MAD, etc? maybe even LAUGHING? I think it was via Bark while using [laugh] and [cough] to make TTS more realistic (without using the Model Interface based on my own recording as reference of course) Thanks ahead! 🙏
I got it working, but trying to do an Arnold Schwarzenegger impression didn't work well. Having to pair it with another similar voice seems to be the weak spot.
Thanks a lot you're so professional in what you do i've learned more in this tutorial more than any other,i do appreciate your time and effort you put into this, you're a good teacher thanks a lot.
They recently changed up the UI and now there's no resource tab. Help! Edit: nvm, the Resource tab is now Download tab.
TTS + RVC, this is exactly what I was waiting for. Thank you !
I love your tutorials. Easy to follow and clear voice.
finaly a tts who works, ty.
how much space does this take up?
@@oisinbroadcast6916 after some work and about 8 samples voices installed 10 gigabytes
1 Gazillion ultrabytes
@@oisinbroadcast6916probably 3-6gb
hello obama
they deleted the fork??
How does one convert text to speech solely using your own voice rather one of the standard voices with this software?
It looks different and I cant find the rvc fork anymore.
This is perfect if you can do your own accents
How good would it sound if the tts (is it tortoise?) voice model would also be of the exact person you want to impersonate and then be send through the rvc part?
hey troublechute, i have a really imp Q and pls replsy asap.
so last year when we had the colab training model, i used multiple colabs to train voice models all days and nights in colab . each of those contained .pth file and .json files.
but now idk weirdly, these new suff are asking for .indx files ??? so how can i turn my .json files into .index files. pls help with this. do i have to train again or what. i dont uinderstand. i havent seen the format of the .index files so am not relaly sure how i can acheive this.
YOU ARE THE BOSS!!! Thank you this is so cool
i hope is not too late but i have a question, does this work for a virtual cable? or is there a way to use it so when the ai voice sounds the people on the other side of a video call on discord would hear it?
how stop or pause train?????
This could be so good, but the base TTS Models are so bad and robotic sounding, and it carries through into the final conversion no matter how well your model is trained. Is there anywhere to get better base TTS Models?? Thanks for the video
Same issue. Keep me posted when you find away to get other tts methods
i do not see UVR in latest appolio , is there some setting to enable it
Tks for your sharing. And how to create dataset of pth from any audio files, like wav, mp3?
Hello, thank you very much for this video, i would like to train/create my onw voice model, how can i do it?
Does anyone know of something like this that can do the TTS in realtime? Not for sure if it is possible, but been looking for a while
Huggingface is showing on the model repo "Detected Pickle imports (23)"
How can we train voice for a specific language?
Getting constant failures building the wheel file for lxml in the windows install bat file. I've tested Python 3.9.10, 3.9.13 (the one you list), 3.10.0 and 3.11, as well as a vcpkg install.
End result is a "ModuleNotFoundError: No module named 'tensorboard'" when running go-applio.bat
Manually installing tensorboard via conda also doesn't resolve it.
same issue
Hello, let's say i want to generate a Text to Speech with a rvc model but I want the speech to be generated following a certain type of accent, emotion and tone, perhaps inserting an audio as a model to instruct the AI to generate the speech with the same tone, accent and emotions as the audio example, how can I do this? it's possible? or to do something like this am I forced to record an audio with my voice and generate it directly from my recorded audio? Thank you in advance guys, wish you the best and a happy new year!
Thank you for such a wonderful tutorial! 💙💙
Can you please explain how to DELETE a model?
After importing SAME models with different versions for testing which is the best, the DROP DOWN LIST became huge.
EDIT:
In case anyone want to know, I found out it's under /logs/weight
Also, is there a way to control the TTS emotion or the "way" things are saying? such as SAD, HAPPY, MAD, etc? maybe even LAUGHING? I think it was via Bark while using [laugh] and [cough] to make TTS more realistic (without using the Model Interface based on my own recording as reference of course)
Thanks ahead! 🙏
How do we uninstall this mate
im pretty new to this and installed rvc from the voice replacing vid through powershell HOW DO I DELETE IT AND WHY DID IT TAKE 15 GB
Just delete the folder. You can uninstall python and other things if you don't use them. See C:\TCHT if you didn't pick an install path manually
i cant see resource tab in new update
I got it working, but trying to do an Arnold Schwarzenegger impression didn't work well. Having to pair it with another similar voice seems to be the weak spot.
You could always try to find a wav where Arnold speaks and use that for training, I guess :)
If I want to add my languages how can I add( If the database of Indian languages is available how can it be added)
Thanks a lot you're so professional in what you do i've learned more in this tutorial
more than any other,i do appreciate your time and effort you put into this, you're a good teacher
thanks a lot.
Work on cpu..?
Is there anyone who can specify the amount of data required in gigabytes?
Please help gradio not install problem
Amigo cadê o arquivo para instalar? Desapareceu?
the era of good quality audiobook wuxia novels is here, praise our AI overlords!
Does it support SSML?
Does not work on Linux
thank for this video .
please can i have your setup folder please 🙏.
how to Install on Mac ?
Thank You for this tutorial, Obama.
this is amazing
Not available for commercial use!
AMD bro?
works in OBS ?¿?¿?¡
how much space does this take? (as in how much MB or GB it takes up)
waiting for you to tell us your last 5 videos were not you actually talking xd
Talking is so much faster than typing, and it would lead to even more effort editing 🤣
@@TroubleChutecan you try that for one vid
this dont work
That was a really good Obama accent.
GIVE US BEST MISTRAL AI ON LINUX/WINDOWS OFFLINE, PLEASE
Shame, another one under dumb license that wont allow commercial usage
this videos voice sounds like AI generated
no it literally doesnt
too many ...
are you serious "obama' I dont like obama
Did he ask you if you liked Obama?
@@knightofcydonia1192 THE WORST PRESIDENT OF USA. I'M BLACK
hello obama