Remove `voice_schemas.py` and refactor schema imports for TTS and ASR modules in `__init__.py`

src/voice_dialogue/api/schemas/__init__.py

@@ -1,13 +1,37 @@
+from .asr_schemas import (
+    SupportedLanguagesResponse,
+    ASRInstanceRequest,
+    ASRInstanceResponse
+)
 from .system_schemas import (
     SystemStatusResponse, SystemResponse
 )
-from .voice_schemas import (
-    VoiceInput, TextInput, VoiceResponse,
-    TTSRequest, TTSResponse, ASRRequest, ASRResponse
+from .tts_schemas import (
+    TTSModelInfo,
+    TTSModelListResponse,
+    TTSModelLoadRequest,
+    TTSModelLoadResponse,
+    TTSModelStatusResponse,
+    TTSModelDeleteResponse,
+    generate_model_id
 )
 
 __all__ = [
-    "VoiceInput", "TextInput", "VoiceResponse",
-    "TTSRequest", "TTSResponse", "ASRRequest", "ASRResponse",
-    "SystemStatusResponse", "SystemResponse"
+    # System schemas
+    "SystemStatusResponse",
+    "SystemResponse",
+
+    # ASR schemas
+    "SupportedLanguagesResponse",
+    "ASRInstanceRequest",
+    "ASRInstanceResponse",
+
+    # TTS schemas
+    "TTSModelInfo",
+    "TTSModelListResponse",
+    "TTSModelLoadRequest",
+    "TTSModelLoadResponse",
+    "TTSModelStatusResponse",
+    "TTSModelDeleteResponse",
+    "generate_model_id"
 ]

src/voice_dialogue/api/schemas/voice_schemas.py

@@ -1,49 +0,0 @@
-from datetime import datetime
-from typing import Optional, Literal
-
-from pydantic import BaseModel, Field
-
-
-class VoiceInput(BaseModel):
-    """语音输入请求模式"""
-    audio_data: str = Field(..., description="Base64编码的音频数据")
-    language: Literal['zh', 'en'] = Field(default='zh', description="语音语言")
-
-
-class TextInput(BaseModel):
-    """文本输入请求模式"""
-    text: str = Field(..., description="输入文本", min_length=1, max_length=1000)
-    language: Literal['zh', 'en'] = Field(default='zh', description="文本语言")
-
-
-class VoiceResponse(BaseModel):
-    """语音响应模式"""
-    transcribed_text: Optional[str] = Field(None, description="转录的文本")
-    generated_text: str = Field(..., description="生成的回答文本")
-    audio_data: str = Field(..., description="Base64编码的音频响应")
-    processing_time: float = Field(..., description="处理时间(秒)")
-    timestamp: datetime = Field(default_factory=datetime.now, description="响应时间戳")
-
-
-class TTSRequest(BaseModel):
-    """文本转语音请求模式"""
-    text: str = Field(..., description="要转换的文本", min_length=1, max_length=1000)
-    speaker: str = Field(default='沈逸', description="语音角色")
-
-
-class TTSResponse(BaseModel):
-    """文本转语音响应模式"""
-    audio_data: str = Field(..., description="Base64编码的音频数据")
-    duration: float = Field(..., description="音频时长(秒)")
-
-
-class ASRRequest(BaseModel):
-    """语音识别请求模式"""
-    audio_data: str = Field(..., description="Base64编码的音频数据")
-    language: Literal['zh', 'en'] = Field(default='zh', description="语音语言")
-
-
-class ASRResponse(BaseModel):
-    """语音识别响应模式"""
-    transcribed_text: str = Field(..., description="识别出的文本")
-    confidence: float = Field(..., description="识别置信度")