GIFT: ๐ใFREE/่คๆฐ็กๆใRVCv2ๅญฆ็ฟๆธใฟใใผใฟ้ซๅ่ณชใใคในใขใใซโฎโNORAโโฏ - NORMAL ONLY
-
bought only the normal version of this nora rvc (aka realtime voice changer), listen to the voice sample yourself to know how it sounds like. also i haven't get to test this out so idk how to setup yet...
note: if you're interested in getting full set instead, it's unnecessary to pay for commercial use, just add all 7 voices individually to cart and it'll be 3500yen (each 500yen) instead! ^^
consider upvoting this post to increase my rep pls ^^

-
H hironoflan referenced this topic on
-
It's great! I am very interested in this field. I hope to see more posts in this area in the future. Thank you!
-
@sekibanki use main repo if you want to make song and voice changing
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/use https://github.com/w-okada/voice-changer if you only want voice changing
-
@sekibanki use main repo if you want to make song and voice changing
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/use https://github.com/w-okada/voice-changer if you only want voice changing
-
I trained few RVC model myself, pretty interesting to see you can sell these. Also the file did not include a .index file, this might impact the overall quality of output voice, not sure it is intentional or not.
@tapple hi! thats very cool, glad to see a rvc model trainer here! i actually do need some help for setting up, hope u dont mind helping cause i've been cracking my brain for almost an entire
i've refered to at the end of this guide by the creator to use as a voice changer, they've provided two options for this: koemake & vc client/okada's voice changer
let's talk about koemake first, the creator mentioned that this is a free program in another guide that is actually light-weight (doesn't use lots of gpu resource) which is great for me. so i signed up their website to download the app and launch it. to my disappointment, despite saying it's free, i could not import any rvc model because it says that i need to buy their premium plan which is usd6, whats even worse is that it's a monthly subscription! would've preferred if it's a one-time payment... at the time of writing this, i just sent a dm to koemake's dev on twitter asking about this cause i'm really disappointed about it (will update about this).
secondly about okada's voice changer, i'm using vcclient_win_std_2.0.78-beta cause i don't have nvidia. unfortunately, the program works very poorly for me. i've increased the chunk even up to the biggest (5 sec) but it takes almost a min to convert and when it does, the result is very choppy and change the gpu to use cpu instead. learned later from someone else that even rtx 4080 may not work properly for this program which is honestly insane. for reference, i think my laptop is considered low end, its intel i5 and intel iris xe, so i concluded that its incompatible.
now about this rvc webui, i'm very confused on how to use this, i'm using RVC1006AMD_Intel which if im not wrong is the released ver of it. it only contains go-realtime-gui.bat, but the program keeps lagging and not responding at all. so i switched to one of the older beta version to use go-web.bat, only to end up confused on whats the purpose of it cause i thought its a web ver of go-realtime-gui.bat...
do you know any alternatives on using this, idk anything about rvc, all ik are apps like voicemod and voice.ai but i think they work differently...
-
@tapple hi! thats very cool, glad to see a rvc model trainer here! i actually do need some help for setting up, hope u dont mind helping cause i've been cracking my brain for almost an entire
i've refered to at the end of this guide by the creator to use as a voice changer, they've provided two options for this: koemake & vc client/okada's voice changer
let's talk about koemake first, the creator mentioned that this is a free program in another guide that is actually light-weight (doesn't use lots of gpu resource) which is great for me. so i signed up their website to download the app and launch it. to my disappointment, despite saying it's free, i could not import any rvc model because it says that i need to buy their premium plan which is usd6, whats even worse is that it's a monthly subscription! would've preferred if it's a one-time payment... at the time of writing this, i just sent a dm to koemake's dev on twitter asking about this cause i'm really disappointed about it (will update about this).
secondly about okada's voice changer, i'm using vcclient_win_std_2.0.78-beta cause i don't have nvidia. unfortunately, the program works very poorly for me. i've increased the chunk even up to the biggest (5 sec) but it takes almost a min to convert and when it does, the result is very choppy and change the gpu to use cpu instead. learned later from someone else that even rtx 4080 may not work properly for this program which is honestly insane. for reference, i think my laptop is considered low end, its intel i5 and intel iris xe, so i concluded that its incompatible.
now about this rvc webui, i'm very confused on how to use this, i'm using RVC1006AMD_Intel which if im not wrong is the released ver of it. it only contains go-realtime-gui.bat, but the program keeps lagging and not responding at all. so i switched to one of the older beta version to use go-web.bat, only to end up confused on whats the purpose of it cause i thought its a web ver of go-realtime-gui.bat...
do you know any alternatives on using this, idk anything about rvc, all ik are apps like voicemod and voice.ai but i think they work differently...
@hironoflan Hiii, unfortunately, I think Intel Xe Graphics likely wonโt handle real-time inference smoothly. RVC itself requires at least a mid-range dedicated GPU to run properly (about >RTX 2060?). Any program using deep learning needs sufficient VRAM (video memory). Integrated graphics share system RAM, which is significantly slower than dedicated VRAM, resulting in much lower performance โ despite newer integrated GPUs might have improved absolute performance compared to older dedicated GPU.
If real-time voice conversion isnโt necessary for you, you can still use RVC1006 go-web.bat for non-real-time processing: upload a pre-recorded audio file and convert it afterward. Do not use older versions, as the latest release features the highly efficient rmvpe pitch extraction algorithm, which delivers far superior results at lower computational cost compared to previous methods.
The go-realtime-gui.bat is only for real time voice conversion, and the go-web.bat is for infer(convert) and training purpose. I see you mention missing go-web.bat? Maybe make your own and test if it works?
runtime\python.exe infer-web.py --pycmd runtime\python.exe --dml --port 7897 pauseAs for VCClient, I used that once, but didn't get any better result compare to RVC one, so I haven't follow it's development.
If you really love the idea of real time voice change, I heard that DDSP might require less resource? I haven't tried this.
And maybe other proprietary software can yield a better result than RVC, but I mainly use RVC for making songs, So I just tried few and stopped. I suggest you DO NOT pay any money to any program that claim "support" RVC but run better, it just repacked RVC code inside I guess?If you into voice clone, something like let a character read text for you, you can try IndexTTS
Hello! It looks like you're interested in this conversation, but you don't have an account yet.
Getting fed up of having to scroll through the same posts each visit? When you register for an account, you'll always come back to exactly where you were before, and choose to be notified of new replies (either via email, or push notification). You'll also be able to save bookmarks and upvote posts to show your appreciation to other community members.
With your input, this post could be even better ๐
Register Login