Wow, the RVC text-to-speech feature definitely surprised me. The voice models are identical to the ones offered by Azure text-to-speech, now that Azure no longer offers free text-to-speech service on their website, this tool definitely comes in handy. Definitely got to try this out.
@@theAIsearch Hi! If I speak English good, but still with an accent (to the ears of a native English person), would training a voice modell with my own English-speaking voice and then applying it to TTS eliminate that, and sound native?
Awesome tutorial. Since the "Installation Files" link doesn't work, just click on the first link and click on "Releases" on the right. There is a step-by-step tutorial on how to install it
Awesome, I can't thank you enough. It worked even with my AMD GPU. I was searching for this for so long and finally got it. RVC never worked for training model on my system. THANK YOU!
@@theAIsearch Hey! It was working fine but now I'm getting errors while extracting features. The last few lines of the error are: {...File "Y:\Applio\Applio-RVC-Fork\env\lib\site-packages\torch n\modules\conv.py", line 306, in _conv_forward return F.conv1d(input, weight, bias, self.stride, RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' Feature extraction completed successfully! } Also, The Train Model cannot detect GPU now!! HELP!! You are my LAST HOPE!
I followede the instructions but the apollio folder only gives me the runtime folder. i already tried rerunning it again but it says applio is already installed
Great videos man... Can u please let me know how u are using that round dynamic voice bars around the influencers images? Highly appreciate ur content man
I saw someone created his own TTS in his own language. It sounds so natural compared to Edge-TTS. How did he do it? He works alone and uses his own voice. I think he uses VITS TTS model.
how to add the model to python? so i can use the tts ok got the app to work but everytime i click convert no audio appears no audio convert not even the nomral modelns nothing
Starting Applio with Conda for Nvidia support... Traceback (most recent call last): File "C:\Users\Admin\Videos vc\Applio-RVC-Fork\infer-web.py", line 3, in from tensorboard import program ModuleNotFoundError: No module named 'tensorboard' Press any key to continue . . . how do i fix this
Traceback (most recent call last): File "D:\applio\Applio-RVC-Fork\infer-web.py", line 26, in import fairseq ModuleNotFoundError: No module named 'fairseq' Press any key to continue . . . @@theAIsearch
nice was looking for something like this since replay doesn't allow tts but sadly atm replay does a better job at similarities to the voice when using it with audio over TTS on apollo idk why?
I know you just made this, but it's already outdated. Critical components have been removed from the installer because they were deemed buggy. It now fails to install needed files for program to open as a result. Any way to update a solution to this? "No Model Named "tensorboard" error.
I get an error when using TTS: File "C:\Users\ivanm\Desktop\Applio-3.0.9\env\lib\os.py", line 822, in fsdecode filename = fspath(filename) # Does type-checking of `filename`. TypeError: expected str, bytes or os.PathLike object, not list
Is there any difference to the result between using this method VS the method mentioned in your video "How to use an Anime Girl Voice in Text To Speech with this FREE AI"?
apparently it uses google translate (for google option) to get the audio then use rvc to change the voice.. unfortunately these ones ain't that good.. would be better if we can find a way to get better voices
they changed things or something I don't have settings OR resources. bothersome given that i wanna use a custom pth location.... o_O Inference Train TTS Extra Download Report
Is there an automated way to do this with RVC? I would like to have a conversation with an AI using this, even if it takes a while for each response. This was the only good video I could find about this, I'm worried that what I want won't be possible...
Click on "Use via API" at the bottom, scroll down to find function index 34 (unnamed). That is your API endpoint for Python. Just got it working on my end. Retrieve index 0 of the result for the path to the altered RVC wav output file and then auto play it or whatever from there.
these atutorials are the worst. merge voices does not work anymore, this one the link doesnt work. and every time i try to contact the guy, no answer back. i have waste SO MUCH time on this channels tutorials
This works great, Im just wondering if there is a way to add emotions to the voicelines? Maybe you could make a tutorial for that? I tried using Tortoise tts but its depreciated as fuck and I didnt get it to work right ...
sadly, i also use tortoise and then convert it using rvc, it sounds clear and good but the voice is so flat unemotional :( maybe you know other free tts? i use elevenlabs but i already ran out my 40k word for this month@@theAIsearch
I've watch many of your videos and they are very informative specially with the how to in google colab. Please make a video on how to run this in google colab. Thank you.
Good video, it's great that someone is creating this type of content. However, I have a problem. After the applio download is successful, when I press a key, the window simply disappears, and the download doesn't continue. I don't know what could be causing this. Any recommendations?
Hello, I have a very important question. Do you think that if I clone the sound of one of the sounds of the library of the eleven labs, copy it and use it in my RU-vid videos, I will get copyright?
Great tutorial! but I got a Error loading "D:\AI\AI voice\TTS\Applio-RVC-Fork untime\lib\site-packages\torch\lib\caffe2_nvrtc.dll" or one of its dependencies. How to slove this? Thanks
Amazing stuff!! I had 1 question tho, when I open “go applio” it’s says: “ModuleNotFoundError: no module named tensorboard” opened go-applio-manager and updated tensorboard. No succes. Any idea what’s wrong? Thanks in advance!!
Hello, I have two very important questions: can this TTS be used to tell scary stories and monetized, and the second question is, does this TTS always work or may it never work at all?
Hi, after I extracting the runtime.zip file, there is nothing but a runtime folder 2:50. I did turn off the antivirus and firewall but it's still the same :(
Hi in Applio Rvc Fork working but in TTS only English text convert and other languages are not so can u provide ur downloaded software or upload it ur drive then we can download it plz
Hey! It was working fine but now I'm getting errors while extracting features. The last few lines of the error are: {...File "Y:\Applio\Applio-RVC-Fork\env\lib\site-packages\torch n\modules\conv.py", line 306, in _conv_forward return F.conv1d(input, weight, bias, self.stride, RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' Feature extraction completed successfully! } Also, The Train Model cannot detect GPU now!! HELP!! You are my LAST HOPE!
your path cant contain a space or you will get error message that sth couldnt be found same with python install use the .exe installer, it lets you choose a path
@@theAIsearch didn't work. apparently right now there isnt a way to use this if you have a space in your user folder... seems silly. I am talking to a dev but I dont think there is a way.
Hey! Loved the tutorial but surprisingly this was harder than the previous RVC installation. I've followed through the steps and downloaded GIT as well but when I get to TTS nothing seemed to happen after I clicked convert. What would be the solution for this?
@@theAIsearchno there was no error messages in applio rvc however in the command prompt there was a line that showed python: can't open file [Errno 2] No such file or directory. Would that be causing the issue?
@@theAIsearchI think I found where the problem was I opened the tts folder and there was only one Suno bark model there I think I'll have to manually download all the edge tts models
@@theAIsearchhmmm I can't help but notice every time I hit convert the command prompt has 2 lines saying lib.infer.modules.vc.modules | Get sid: logs /weights\Obama.pth then the second line is lib.infer.modules.vc.modules | Loading ... with another line after that saying 'config'
It's not working for me, everytime i try to install it it says that i'm running it with administrator priviligies, although i'm not. So, i've download the .exe and it was installed, but... when it comes to running the program, it doesnt i get all sort of different messages like torch not being installed, etc. I've installed it manually pretty much every error i found in cmd, but... idk, i feel like it shouldn't be that way. Now i'm getting an error that i didn't found a resolution yet: line 12, in from torch.nn.utils.parametrizations import spectral_norm, weight_norm ImportError: cannot import name 'weight_norm' from 'torch.nn.utils.parametrizations' And i'm sure that when i fix it (if i fix it), i'll get another erro. I've fixed more than 10 erros. Would u know why is that happening?
why does it need to convert? why you gotta hhoose a tts model? why cant it talk in ...lets say ai anime voice directly? the way i undertood is. the programm listens to the ai voice lets say an amerkian accent and the converts it into the wished ai voice. but isnt there a way to shorten it even further? isnt there a way ? like you can choose an tts model why cant you choose a ai voice changer model instead? and just let it speak direktly
@@theAIsearch Thanks you man for the tutorial, I installed. That Work fine. But if i put bark tts, that need many Times. So i keep the Edge tts for the moment. Thanks you 👍