VIBEVOICE RVC BEST TTS AI VOICE CLONING WORKFLOW!
Added 2025-09-20 18:42:50 +0000 UTCHey everyone! I’ve just released a brand-new video on “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
I also created a 1-click installer for the Webui for my Patreon supporters for Local AND Runpod, that you can find right here: https://www.patreon.com/posts/139346699
As well as the installer for the Vibevoice & RVC webui: https://www.patreon.com/posts/139346683
Here the link to the manual install guide: https://pastebin.com/FX07hPLc
Down below you will also find the VIBEVOICE-RVC_VOICE_CLONING.json for free for you to use!
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
Another failed attempt. No models installed. I'm sorry but this is getting silly. The scripts for local install always give problems (gave up on runpod) . I need to spend hours fixing things and trying to locate models etc.. I like the videos you put out but please include clear instructions where to get the models in case your scripts fail to work. I don't mind downloading things manually but I hate to search for them and "guessing"which one is the correct one
Väinämöinen
2025-10-30 00:04:01 +0000 UTCAfter starting RVC training, an error occurs regardless of whether the graphics card is 4090 or 5090. Does anyone know how to fix this? Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 108, in run File "D:\AI\RVC1006Nvidia\infer\modules\train\train.py", line 132, in run dist.init_process_group( File "D:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\distributed\distributed_c10d.py", line 888, in init_process_group store, rank, world_size = next(rendezvous_iterator) File "D:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\distributed\rendezvous.py", line 245, in _env_rendezvous_handler store = _create_c10d_store(master_addr, master_port, rank, world_size, timeout) File "D:\AI\RVC1006Nvidia\runtime\lib\site-packages\torch\distributed\rendezvous.py", line 176, in _create_c10d_store return TCPStore( RuntimeError: unmatched '}' in format string
Cooper Huang
2025-10-17 01:35:39 +0000 UTCSame (Used the VIBEVOICE-RVC-NODES_INSTALL.bat because I had ComfyUI allready installed)
Tomi Räsänen
2025-10-12 05:21:01 +0000 UTCi ran the autoinstaller but there are no models included. where do i get the VibeVoice model?
SmallFox
2025-10-06 13:45:52 +0000 UTCStuck at 0% with the below msg using comfi ui For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet` Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet` Xet Storage is enabled for this repo, but the 'hf_xet' package is not installed. Falling back to regular HTTP download. For better performance, install the package with: `pip install huggingface_hub[hf_xet]` or `pip install hf_xet`
Vanz Watts
2025-09-23 12:21:09 +0000 UTCI have tried everything. and when I go to generate it just never goes past zero%. I am not sure what i am doing wrong. I followed the video and read the instructions and still nothing.
Vanz Watts
2025-09-23 10:46:03 +0000 UTCI tried downloading the large model and got a out of memory error. I have 8 gb of vram. Anything I can do?
Dropbear 21
2025-09-21 23:04:05 +0000 UTCI've heard that disabling sageattention in the run bat file can fixe the issue
Aitrepreneur
2025-09-21 21:15:03 +0000 UTCSo getting errors with this specific custom node, which has been fixed in the upstream custom-node which also uses SafeAttention: VibeVoiceMultipleSpeakersNode Error generating multi-speaker speech: VibeVoice generation failed: 'DynamicCache' object has no attribute 'key_cache'
James Charleston II
2025-09-21 20:21:46 +0000 UTC
