3-in-1 Workflow for Voice Cloning, Image-to-Video, and Video-to-Video with Lip Sync!
🕑 Added 2025-01-21 21:58:38 +0000 UTCTutorial for the AUDIO workflow.
Updated workflows available here: https://www.patreon.com/posts/comfyui-studio-111135526
Workflow update archive v190 is updated.
Comments
Paulo Chiovatto
you can add another language portuguese brazil
国伟 陈
Hi, are you guys have plan to add Zonos?
DigitAll
Then add the C:/ffmpeg/bin to system path manually
foxi
yes
ricardo palmieri
sent you a PM on discord.
ricardo palmieri
Anybody knows how to use Brazilian Portuguese?
DigitAll
Did you run the ffmpeg install script?
foxi
Ok, I thought when doing a restart from the UI manager it would be enough to update the ffmpeg integration, but finally when I closed comfyui completely and restarted the application, it worked. My bad I guess
foxi
I understood after my message, I made a copy of the folder on my C:\ then I followed the steps. Normally, it succeeded but for no reason, the same error message is displayed "Apply Whisper [WinError 2] The specified file could not be found"
DigitAll
6-Apps folder has the ffmpeg
foxi
i followed the guide to install ffmpeg, but the script dont work and on my system windows i dont have any folder called ffmpeg. So what i should do next ? Thx
João C R Fonseca
Is there any way to add Brazilian Portuguese to this workflow?
v33ts
I figured it out, I had two latent sync custom nodes, one conflicted with the other. Thanks for the offer of help though.
DigitAll
Install ffmpeg
DigitAll
Write me on discord
Dinesh Raj R
iam gettig this error Apply Whisper [WinError 2] The system cannot find the file specified how to fix need help # ComfyUI Error Report ## Error Details - **Node ID:** 35 - **Node Type:** Apply Whisper - **Exception Type:** FileNotFoundError - **Exception Message:** [WinError 2] The system cannot find the file specified ## Stack Trace
Dinesh Raj R
any model for Tamil Voice please
v33ts
Looks like an update broke it :( - Latent Sync Video wont accept the images from Latent Sync node.
DigitAll
There is not available f5 tts arabic on hugging face
IAM
any update
IAM
thanks, there are only 11 languages, i would like to feed Arabic audio as a sample, and the Arabic text to audio can output, will be my objective
DigitAll
Will check
IAM
Hi any model to get arabic voice
justin ruscheinski
Wish it worked with my RTX 3060