This FREE Text-To-Speech Does Everything – OMNIVOICE for ComfyUI
OMNIVOICE is the ultimate free Text-to-Speech model. Clone voices, design custom voices, and generate multi-speaker conversations easily in ComfyUI.
links:
https://docs.comfy.org/installation/c...
https://git-scm.com/install/windows
https://github.com/Comfy-Org/ComfyUI-...
Omnivoice:
https://github.com/k2-fsa/OmniVoice?t...
custom node for Omnivoice:
https://github.com/Saganaki22/ComfyUI...
https://github.com/Saganaki22/ComfyUI...
https://github.com/Saganaki22/ComfyUI... (troubleshooting)
Installation command:
git pull https://github.com/k2-fsa/OmniVoice.git
.\python_embeded\python.exe -m pip install torch==2.9.0 torchvision==0.24.0 torchaudio==2.9.0 --index-url https://download.pytorch.org/whl/cu128
.\python_embeded\python.exe -m pip install torchcodec==0.9.0 --index-url https://download.pytorch.org/whl/cu128 (ignore if error)
.\python_embeded\python.exe -m pip install omnivoice
Workflow:
============================================
https://drive.google.com/file/d/1w4zG...
============================================
#TextToSpeech #TTS #OMNIVOICE #ComfyUI #FreeTTS #AIVoice #VoiceCloning #MultiSpeakerTTS #VoiceDesign #LongAudioGeneration #OpenSourceTTS #AIVoiceover #CustomTTSVoices #ExpressiveTTS
Optional support if you want to help the channel:
paypal:
[email protected]
00:00 - Intro
01:15 - workflow OVERVIEW
06:12 - Installation