Aitrepreneur
patreon
1-Click INSTALL VIBEVOICE & RVC WEBUI!
🕑 Added 2025-09-20 18:43:05 +0000 UTCHey 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 installer of course automates the entire install process for the Vibevoice Webui & RVC Webui.
Local install:
Requisites:
– CUDA 12.8
– Git, Python 3.10 64-bit, 7zip, ffmpeg
FFMPEG-INSTALL AS ADMIN.bat ---> This one installs FFMPEG, run as admin
RVC_INSTALLER.bat ---> This one installs the RVC webui, choose 1 or 2 depending on your GPU
RVC_INSTALL-RUNPOD.sh ---> This one installs the RVC webui on runpod
VIBEVOICE-WEBUI_INSTALLER.bat ---> This one installs the Vibevoice webui
VIBEVOICE-WEBUI_INSTALL-RUNPOD.sh ---> This one installs the Vibevoice webui on runpod
FOR Vibevoice RUNPOD:
1. Create an account if you haven't already: Runpod
2. Click on Pod (on the left side) then click deploy
3. Choose a 4090 GPU and chose the pytorch 2.1 then edit the template and choose 50GB for both the container and volume disk
then scroll and click deploy.
4. Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 8888"
5. Then drag and drop the VIBEVOICE-WEBUI_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI
6. Copy and paste these two lines then press enter:
chmod +x VIBEVOICE-WEBUI_INSTALL-RUNPOD.sh
./VIBEVOICE-WEBUI_INSTALL-RUNPOD.sh
7. Wait for everything to be installed
8. Click on the public url to launch the webui
FOR RVC RUNPOD:
1. Create an account if you haven't already: Runpod
2. Click on Pod (on the left side) then click deploy
3. Choose a 4090 GPU and chose the pytorch 2.1 then edit the template and choose 50GB for both the container and volume disk, then under expose ports, edit:
8888 into 8888, 7865.
then scroll and click deploy.
4. Go to my pods, wait for everything to finish and then click "connect", then "Connect to HTTP SERVICE port 8888"
5. Then drag and drop the RVC_INSTALL-RUNPOD.sh file on the left side of the UI then click on the "Terminal" icon on the right side on the UI
6. Copy and paste these two lines then press enter:
chmod +x RVC_INSTALL-RUNPOD.sh
./RVC_INSTALL-RUNPOD.sh
7. Wait for everything to be installed
8. Go back to the port 7865 and click on it to launch the webui
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😉!
Comments
Damian Smith
keep getting an error with the web ui installer
Luke Walter
Same here, what's going on???
FILMTOOLS LINZ
I hear music along with voice when I generate audio why? how to turn it off I can't figure it out
JAMES M BOWEN
can someone help? I am so stumped, i did the local install, and everytime i generate i get his error, ❌ Error: No audio chunks were received from the model. Generation time: 1.13s.
Sabsabinx
Brilliant - Worked perfectly first time, and the results are superb! Thanks K
robin poirieux
ok simply reboot system after installing this tool. No more errors after that, it works fine ! Amazing tool !
robin poirieux
installation OK, custom speaker done, but the generation returns an error : \VibeVoiceTTS\.venv\lib\site-packages\pydub\utils.py:198: RuntimeWarning: Couldn't find ffprobe or avprobe - defaulting to ffprobe, but may not work warn("Couldn't find ffprobe or avprobe - defaulting to ffprobe, but may not work", RuntimeWarning) batch FFMPEG-INSTALL AS ADMIN.bat not working ?
Chris Bane
exactly the same issue with rtx 5090 and one click installer. try to install the comfy ui version which works fine on rtx5090
Lance Fanger
Does VibeVoice webui work with CUDA 13?
Torsten
I used your 1-click installer but can´t get it to work. I am running a RTX 5090 with newest CUDA installed but always get this error: Error in generation thread: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1 Compile with TORCH_USE_CUDA_DSA to enable device-side assertions
Jaybli
I've downloaded the large model (webui), and loaded it correctly (I think), But halfway through generating this error pops out: File "C:\Users\Blank\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 1440, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified
