BREAKING
OmniVoice TTS comes to ComfyUI
0
+
languages
0
k
hours trained
0
released ~April
0
x
real-time speed
0
kHz
output
0
s
max reference
What the ComfyUI nodes do
1
Voice cloning
↓
2
Text voice design
↓
3
Multi-speaker dialogue
↓
4
Laughter & sighs
Strengths vs limitations
Strengths
●
Low-resource language support
●
Cloning near commercial tools
●
Expressive non-verbal output
Limitations
●
Unstable voice design
●
Dependency conflicts
●
Trouble with long audio
Multilingual speech in your nodes
AI NEWS BLITZ
OmniVoice, a zero-shot text-to-speech model, now runs inside ComfyUI workflows.