feat: Integrate IndexTTS2 model and update related schemas and frontend components

qwen3-tts-backend/schemas/audiobook.py

@@ -31,6 +31,7 @@ class AudiobookCharacterResponse(BaseModel):
     description: Optional[str] = None
     instruct: Optional[str] = None
     voice_design_id: Optional[int] = None
+    use_indextts2: bool = False
 
     model_config = ConfigDict(from_attributes=True)
 
@@ -69,6 +70,7 @@ class AudiobookCharacterEdit(BaseModel):
     description: Optional[str] = None
     instruct: Optional[str] = None
     voice_design_id: Optional[int] = None
+    use_indextts2: Optional[bool] = None
 
 
 class AudiobookSegmentResponse(BaseModel):

qwen3-tts-backend/schemas/tts.py

@@ -51,3 +51,10 @@ class VoiceCloneRequest(BaseModel):
     top_k: Optional[int] = Field(default=50, ge=1, le=100)
     top_p: Optional[float] = Field(default=1.0, ge=0.0, le=1.0)
     repetition_penalty: Optional[float] = Field(default=1.05, ge=1.0, le=2.0)
+
+
+class IndexTTS2FromDesignRequest(BaseModel):
+    voice_design_id: int
+    text: str
+    emo_text: Optional[str] = None
+    emo_alpha: float = Field(default=0.6, ge=0.0, le=1.0)

qwen3-tts-backend/schemas/voice_design.py

@@ -19,6 +19,7 @@ class VoiceDesignResponse(BaseModel):
     aliyun_voice_id: Optional[str]
     meta_data: Optional[Dict[str, Any]]
     preview_text: Optional[str]
+    ref_audio_path: Optional[str] = None
     created_at: datetime
     last_used: datetime
     use_count: int