🎛️ TTS All-In-One Unified Panel
Current Mode
Current Model
Voice Clone
CustomVoice
Podcast
Style Instruction
TTA
Speech with BGM
Voice Clone
CustomVoice
Podcast
Style Instruction
TTA
Speech with BGM
Qwen3-TTS
Fun-CosyVoice3-0.5B
SoulX-Podcast-1.7B
MOSS-TTS
MOSS-TTSD-v1.0
MOSS-VoiceGenerator
Ming-Omni-TTS
Qwen3-TTS
Fun-CosyVoice3-0.5B
SoulX-Podcast-1.7B
MOSS-TTS
MOSS-TTSD-v1.0
MOSS-VoiceGenerator
Ming-Omni-TTS
🎨 Style & Design
Style Instruction / Voice Description
展现出悲苦沙哑的声音质感,语速偏慢,情绪浓烈且带有哭腔,以标准普通话缓慢诉说,情感强烈,语调哀怨高亢,音高起伏大。
👤 SPK1 Clone
SPK1 Audio
Drop Audio Here
- or -
Click to Upload
SPK1 Text
👥 SPK2 Clone
SPK2 Audio
Drop Audio Here
- or -
Click to Upload
SPK2 Text
📝 Synthesis
Target Text / Script
[S1] 哈喽，AI时代的冲浪先锋们！欢迎！ [S2] 欢迎啊！
Language
Speaker
Model Size
Seed
🚀 Start Generating Audio
Final Generated Audio
System Status