3arabic-TTS VoiceDesign Inference
VoiceDesign model (caption-conditioned). Choose a style from the dropdown.
Model Device
Model Precision
Codec Device
Codec Precision
Text
Caption / Style Prompt (اختر من القائمة)
Sampling
▼
Num Steps
↺
1
120
Num Candidates
↺
1
32
Seed (blank=random)
Seconds (blank=auto from text length)
Duration Scale
↺
0.5
1.5
Time Schedule
Sway Coeff
↺
-1
1.5
CFG Guidance Mode
CFG Scale Text
↺
0
10
CFG Scale Caption
↺
0
10
Advanced (Optional)
▼
Generate
Generated Audio 1
Run Log
Timing