🎯 Choose Your Template
🧠 Smart Voice - Generate natural speech based on context
🔧 System Configuration
✍️ Your Text
Character count: 116
128 4096
0 1.5
0.1 1
-1 100
0 10
1 10
Stop Strings
Stop Strings
<|end_of_text|> |
📊 Generation Status
Ready to generate speech...
💬 Model Response
🎵 Generated Audio
💡 Quick Tips:
- For voice cloning, upload a clear 10-30 second audio sample
- Use [music start] and [music end] tags for background music
- Add [SPEAKER0] and [SPEAKER1] tags for multi-speaker dialogue
- Experiment with temperature (0.8-1.2) for varied speech styles