Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

1-Click INSTALL VIBEVOICE RVC ComfyUI WebUI! (Patreon)

Published:
2025-09-20 18:43:19
Edited:
2025-09-20 21:59:39
Imported:
2026-06
Tags:

Downloads

Content

Hey everyone! I've created a 1-click installer for “The ULTIMATE Local TTS AI Voice Cloning”, featuring the brand-new VibeVoice model. This one is a total game-changer it can clone voices with as little as 10 seconds of audio, generate conversations between up to 4 voices at the same time, and even switch across multiple languages… all running locally on your own computer. 👀🎤

You can check out the video right here: https://youtu.be/XtaPZmlyMMw

The workflow: https://www.patreon.com/posts/139346669

The installer of course automates the entire install process for comfyUI and the nodes downloads!

LOCAL INSTALL!!! RECOMMENDED TO START FROM SCRATCH SINCE YOU NEED THE LATEST COMFYUI TORCH VERSION!!!

Download the VIBEVOICE-RVC-COMFYUI-MANAGER_AUTO_INSTALL.bat

Run the bat file

Wait for the install to finish

The webui will launch, load the VIBEVOICE-RVC_VOICE_CLONING.json file and there you go😎

DON'T FORGET TO GO UPDATE COMFYUI BY GOING INSIDE THE UPDATE FOLDER AND RUNNING THE COMFYUI UPDATE BAT FILE!!!!

IF YOU ALREADY HAVE COMFYUI INSTALLED USING A PREVIOUS INSTALLER:

Download the VIBEVOICE-RVC-NODES_INSTALL.bat and place it in the ComfyUI_windows_portable\ComfyUI folder

Run the bat file

Wait for the install to finish

???

Profit 😎

IF YOU GET AN ERROR WHEN LAUNCHING COMFYUI AFTER USING THIS INSTALLER SAYING "AssertionError: Torch not compiled with CUDA enabled" it's ok don't panic.

Just go inside the python embedded folder, click on the folder path, type cmd press enter, this will bring the command prompt window and there type:

python.exe -m pip uninstall torch

python.exe -s -m pip install --upgrade torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128

--->replace cu128 by your cuda version (if you don't know your cuda version just open a new cmd window and type nvcc --version it will then tell you at the end Cuda compilation tools, release 12.8, V12.8.93 or something different like 12.6, in that case just use cu126 instead of cu128)

IF YOU ARE USING RUNPOD:

Create an account if you haven't already: Runpod

Click on Pod (on the left side) then click deploy

Choose a GPU with at least 24gb of VRAM (4090 is best), click here for the comfyui template (aitrepreneur/comfyui), then edit the template and choose 100gb for both the container and volume disk, then deploy on demand

Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 3000" and click on the manager to update comfyui and restart it

Then go to the port 8888, go inside the comfyui folder and then drag and drop the VIBEVOICE-RVC-AUTO_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI

Copy and paste these two lines then press enter:

chmod +x VIBEVOICE-RVC-AUTO_INSTALL-RUNPOD.sh

./VIBEVOICE-RVC-AUTO_INSTALL-RUNPOD.sh

Wait for everything to be installed

Go back to the port 3000 and click on the manager and restart it, refresh with F5

Load the VIBEVOICE-RVC_VOICE_CLONING.json file and there you go😎

Also use the command:

tail -f comfyui.log

inside the workspace/logs to get the real time logs so that you always know when the install is done. It will then ask you to restart, so click on that restart button, wait for the webui to reboot, click refresh once it's done and there you go.

As always, supporting me on Patreon allows me to keep creating helpful resources like this for the community. Thank you for your support - now go have some fun😉!

Files

Comments

Midnight

Thank you! P.S I think you need to fix your post it still references "QWEN IMAGE EDIT" at the top unless I'm misunderstanding. I use templates all the time at work. It's embaressing when I send an email to a customer and forget to edit a section. So I understand. lol

Roy F

Thank you so much! This looks awesome. If I train VibeVoice with my voice for a single speaker with more than 10 minutes of audio using the RVC UI, will I get much better results than with just 10 seconds? Have you tried with longer audio?

Brian Monarch

For some reason I get "Some Nodes Are Missing - When loading the graph, the following node types were not found. This may also happen if your installed version is lower and that node type can’t be found." I've tried the nightly version of this node and the latest version. Is this workflow compatible with Blackwell cards or am I just missing something? Thanks!!!

Brian Monarch

I tried VibeVoice last week, and I was getting better results with a 48 second sample of someone than I did with a 10 minute sample of them. But that's just from my quick tests.

Aitrepreneur

There is a limit on the webui on how long the audio file sample can be, so it can't be 10 minutes long

Aitrepreneur

Have you used the installer? and have you update comfui to the latest version using the update comfyui bat file inside the update folder?

Brian Monarch

No, I just dropped the JSON file in there and updated the nodes. I didn’t even see the installer. I’ll look closer. Thanks!

Vanz Watts

I'm lost. I installed everything but IDK how to launch it

Brian Monarch

Yeah, I was using the comfyui version. But that version didn't have the RVC add on.

Brian Monarch

I used the one click installer and everything is working, but I don't see where the pth and index files are. There's no folder in my models folder called TTS. (By the way... My models folder is on my E drive and my Comfyui installation is on my D drive.) But there isn't a TTS folder in either models folder on either drive. I created one where my other models are but it doesn't see those files in RVC. BUT, it does see the ones that came with it, like Monika etc... I did a search for the word monika and I can't find where those files are. I'm very confused by this if you happen to know what's going on. Thanks!!!

John Jan

Iam getting the exact same error

Chris Bane

it doesn't work on rtx 5090. getting error even if i run random example - ❌ Error: No audio chunks were received from the model. Generation time: 1.02s. is it possible that you will create in click installation for rtx 5090?

Wojtek Mazur

Trying out the WebUI for Voice Cloning, from the latest video. Starts singing half way the text 😄 also random musical chimes are a common thing. Anyone has a way around that?

Wojtek Mazur

C:\Windows\System32\VibeVoiceTTS\LAUNCHER_VibeVoice.bat

Nedo Braun

Comfyui version works for me on my rtx5090, but the Webui version dont work, same error ase you: ❌ Error: No audio chunks were received from the model. Generation time: 1.02s.

Bob Winberry

for some reason I am unable to install the RVCEngineNode - and I've updated everything, even tried going through git - but it just doesn't install. Any idea? thanks (hope you're feeling better)

Omar Morales

I am trying to switch from a cloud based solution to a local llm gpu , any recommendations to buy? I was looking at some 24gb vram options like the 3090 card but any help is appreciated

Aitrepreneur

you just need to do a "blank run" and all the models and folders will be downloaded automatically, I explain it at the end of the video

Aitrepreneur

Make sure that you have python 3.10 and cuda 12.8 installed correctly. I know that this works on runpod with a 5090

rfromp

Python version is: 3.10.11 Cuda version: 12.8 Yep, the first thing I did was to check the versions. Are these correct?

tony

I followed the tutorial and am able to generate audio. But on re-launching ComfyUI noticed several nodes in this and other workflows show up as red "undefined" nodes. Something as simple as WanImagetoVideo is gone. Worse, the ComfyUI Manager is also gone, so I have no way of updating anything. Could really use some help, adding this .bat and workflow has nuked the rest of my ComfyUI on Runpod.

rfromp

DM sent!

Ghost

I'm completely new to this kinda thing and I'm trying to follow the tutorial for the local version without Runpod and I keep getting this error : Error generating multi-speaker speech: Model loading failed: Allocation on device not sure what I might be doing wrong. If anyone has any answers for a complete noob that would be nice thank you!

James Charleston II

Hello, New here but not new to comfyUI. I have it installed in a lot of local instances as well as many runpod. I am trying to install with your local script and getting alot of errors. I am working through fixing them, which requires a lot of items to be installed. Is anyone else having issue with the 1 click installer?

James Stewart

Hi K, the audio quality from your video on Vibe Voice was exceptional. But I love how your video a year ago integrated txt generation and trained audio voices into SillyTavern. Any chance of a new video on how to use Vibe Voice in SillyTavern with all the same *creative roleplay* aspects of the old video?

JW

Hi, supporter here. I downloaded the tts model files directly due to connection issues, but every time I try to run the workflow, it tries again to download the files and it fails. What can I do to get around this? E:\ComfyUIforWan2\ComfyUI_windows_portable\ComfyUI\models\tts\aoi-ot\VibeVoice-Large got prompt Executing prompt: bd9c9988-ac0b-4bf8-81e7-f8e55d4b0a27 E:\ComfyUIforWan2\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda\memory.py:491: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats. warnings.warn( 🎵 Loading RVC Model: Monika.pth ✅ RVC model loaded successfully APEX FusedRMSNorm not available, using native implementation [VibeVoice] Using embedded VibeVoice from E:\ComfyUIforWan2\ComfyUI_windows_portable\ComfyUI\custom_nodes\VibeVoice-ComfyUI\vvembed [VibeVoice] Using auto attention implementation selection [VibeVoice] Loading model from local cache: aoi-ot/VibeVoice-Large [VibeVoice] Downloading aoi-ot/VibeVoice-Large... Fetching 10 files: 0%| | 0/10 [00:00

Wooden_Nickel

I've had grok trying but I'm just not getting this to run on Linux, by chance has anyone had any luck

Vanz Watts

So I have everything installed but when i click generate it starts but it never generates, I left it on over night to see if it would work after some time and still nothing. I am not sure what I am doing wrong.

Gordon Wegener

My 5090 is still 8 stops away :-( Going to test afterwards

James Charleston II

Hello, fresh complete install is failing: Error generating multi-speaker speech: Model loading failed: VibeVoice embedded module import failed. Please ensure the vvembed folder exists and transformers>=4.51.3 is installed.

James Charleston II

just a follow up. The installer was breaking out of the portable python. I updated the configuration to make sure python portable was used, especially when installing the dependencies of the custom_nodes. I also lost the hf_xet. Downloading models now, and will see if there are any other issues.

LW

Thanks again K! This is fun. Just run a few times but already noticed a few things. Long sample is not always best. Seed makes a significant difference, sometimes producing a garbled mess.. ok, no big surprise there! Does anyone know how to specify emotion? So for example, boredom, excitement, sadness. And dramatic pauses? Pauses to catch breath?

LW

ah ha... inserting [pause] ... with square brackets... inserts a 1 sec pause. [pause] [pause] inserts a 2 second pause.... hmmm progress!

Rampa

Thanks, I obviously could just try, but I'm curious : How long does it take to generate the voice ? For example to generate 10 seconds of voice

Peter J Walker

RVCEngineNode can not find this node do you have a link, it did no install with your node installer.

contrite831

Hey Pal, you might have "ComfyUI_ChatterBox_SRT_Voice" nodes package installed, this is an outdated package that conflicts with RVCEngineNode and makes it look like you are missing it. If you uninstall that package and refresh it should work. Hope this works for you.

contrite831

Hey Pal, you might have "ComfyUI_ChatterBox_SRT_Voice" nodes package installed, this is an outdated package that conflicts with RVCEngineNode and makes it look like you are missing it. If you uninstall that package and refresh it should work. Hope this works for you.

Peter J Walker

yes I did have it installed dive uninstalled it will try again in while :/

Bob Winberry

Thanks for info - I'll check it out

Tommario Minor

RVC Engine node seems to break COMFY for me. I back up my comfy install on another drive. all workflows are working fine but the vibevoice is showing missing model RVC engine. I run the the install.bat file for the RVC engine and it breaks the entire comfy install.

Randy Roberts

Hello, I get the following error in ComfyUI VibeVoiceMultipleSpeakersNode Error generating multi-speaker speech: Model loading failed: Failed to load VibeVoice processor. Error: expected str, bytes or os.PathLike object, not NoneType Please ensure transformers>=4.51.3 is installed. Any idea on how to fix this? Thanks

Enes Çelik

You need to install Python 3.10.11 and pip 23.3.1. They're the source of the problem. Installing these Python and pip packages shouldn't cause any problems.

Tommario Minor

JUST RE RAN FRESH INSTALL FOR VIBE VOICE. IT JUST SAYING NO MODELS FOUND. UPDATED COMFY AND RAN VIBEVOICE-RVC-NODES_INSTALL. SAME ERROR, NO MODELS FOUND

tony

"The workflow you've loaded has corrupt linking data."

Jenee Cooling

I made a lot of changes trying to get things to work, I ended up removing the "VibeVoiceMultipleSpeakersNode" and adding in "VibeVoiceTTS" - it runs now and seems to be working alright. I was getting an error about the qwen tokenizer before I made the change.

Chad Mercer

I tried using the Runpod install script, but it failed on a brand new Pod. I had to manually clone ComfyUI before the script would work. May be worth updating that script to either clone ComfyUI where it should be or tell the user how to do so. git clone https://github.com/comfyanonymous/ComfyUI

Clinton

I just got through watching the video and can't wait to try this out. One question: since Vibe is text to speech, I get the feeling that all the emotion and variation is based on the variety in the sample clip. Is there any way to override or help guide the variety, like slowing down, whisper, yelling certain things that are typed in?. Or would I simply use RVC to replace my voice reading the text with a trained voice?

SmallFox

Wher do I download the Voice Model??????

SmallFox

I Ran the AutoInstaller for Comfyui but when I add an Audio file and try run it I get the following.... Prompt execution failed Prompt outputs failed validation: VibeVoiceMultipleSpeakersNode: - Failed to convert an input value to a INT value: seed, randomize, invalid literal for int() with base 10: 'randomize' - Value not in list: model: 'VibeVoice-Large' not in ['No models found'] - Value not in list: quantize_llm: 'True' not in ['full precision', '4bit', '8bit'] - Value 0.0 smaller than min of 0.5: cfg_scale LoadAudio: - Custom validation failed for node: audio - Invalid audio file: PTT-20250906-WA0000.opus VibeVoiceMultipleSpeakersNode: - Failed to convert an input value to a INT value: seed, randomize, invalid literal for int() with base 10: 'randomize' - Value not in list: model: 'VibeVoice-Large' not in ['No models found'] - Value not in list: quantize_llm: 'True' not in ['full precision', '4bit', '8bit'] - Value 0.0 smaller than min of 0.5: cfg_scale

FILMTOOLS LINZ

yeah what is up with the music I also get that

FILMTOOLS LINZ

this does not work i have try it nothing gets downlaoded on the first run for me

Otniel Ocampo

I'm getting the same error on a new install I did! Did you ever found the answer. I'm trying migrating the Large model from WebUI to ComfyUI but I don't know where to put it

SmallFox

Unfortunately not, I've had little help here. I've just been using the webui version for now until I get a helpful reply. If you manage to figure it out please let me know.

Capi A

this tool is amazing, thank you so much. Link us the large model no? xd

Cristo

Is this working? I tried to autoinstall on runpod but it doesn't download anything.

Patrick Brown

contrite831, this really helped me out. Thanks so much.

Peter J Walker

thank you very much for completely screwing up m install of comfui which I'm having to completely reinstall. THANK YOU

Stephen Antcliff

Would be great for Mac Installers too. Can't use windows .bat files on a mac

MadG

Have you been able to get this to work with SillyTavern? Through Comfyui i guess huh?

Tiago Fernandes

It is not working for me. I installedd the Vibevoice-RVC-Comfyui-Manager-Auto_Install and for some reason it did't download the model. I manually download it, and placed on the folder that Comfyui tells me that it should be, "vibevoice" in the folder models, still, Comfyui can't find it.

DarkCry

Your link for comfyui template (aitrepreneur/comfyui) is not a link

wali wed

no esta el flujo de trabajo

wali wed

me sale error