feat: 添加TTS相关配置和功能

- 在.env.example中添加TTS模型、语音名称和语速的配置选项
- 更新README文件，增加TTS相关配置的说明
- 在配置类中添加TTS相关设置
- 新增TTS请求模型以支持文本转语音功能
- 更新智能路由中间件以支持音频请求
- 在路由中添加处理TTS请求的API接口
- 更新前端配置编辑器以支持TTS配置选项

app/config/config.py

@@ -77,6 +77,11 @@ class Settings(BaseSettings):
     THINKING_MODELS: List[str] = []
     THINKING_BUDGET_MAP: Dict[str, float] = {}
 
+    # TTS相关配置
+    TTS_MODEL: str = "gemini-2.5-flash-preview-tts"
+    TTS_VOICE_NAME: str = "Zephyr"
+    TTS_SPEED: str = "normal"
+
     # 图像生成相关配置
     PAID_KEY: str = ""
     CREATE_IMAGE_MODEL: str = DEFAULT_CREATE_IMAGE_MODEL

app/domain/openai_models.py

@@ -33,3 +33,10 @@ class ImageGenerationRequest(BaseModel):
     quality: Optional[str] = None
     style: Optional[str] = None
     response_format: Optional[str] = "url"
+
+
+class TTSRequest(BaseModel):
+    model: str = "gemini-2.5-flash-preview-tts"
+    input: str
+    voice: str = "Kore"
+    response_format: Optional[str] = "wav"

app/middleware/smart_routing_middleware.py

@@ -67,9 +67,9 @@ class SmartRoutingMiddleware(BaseHTTPMiddleware):
             r"^/gemini/v1beta/models/[^/:]+:(generate|streamGenerate)Content$",  # Gemini带前缀
             r"^/v1beta/models$",  # Gemini模型列表
             r"^/gemini/v1beta/models$",  # Gemini带前缀的模型列表
-            r"^/v1/(chat/completions|models|embeddings|images/generations)$",  # v1格式
-            r"^/openai/v1/(chat/completions|models|embeddings|images/generations)$",  # OpenAI格式
-            r"^/hf/v1/(chat/completions|models|embeddings|images/generations)$",  # HF格式
+            r"^/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # v1格式
+            r"^/openai/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # OpenAI格式
+            r"^/hf/v1/(chat/completions|models|embeddings|images/generations|audio/speech)$",  # HF格式
             r"^/vertex-express/v1beta/models/[^/:]+:(generate|streamGenerate)Content$",  # Vertex Express Gemini格式
             r"^/vertex-express/v1beta/models$",  # Vertex Express模型列表
             r"^/vertex-express/v1/(chat/completions|models|embeddings|images/generations)$",  # Vertex Express OpenAI格式
@@ -146,6 +146,8 @@ class SmartRoutingMiddleware(BaseHTTPMiddleware):
                 return "/openai/v1/embeddings", {"type": "openai_embeddings"}
             elif "image" in path.lower():
                 return "/openai/v1/images/generations", {"type": "openai_images"}
+            elif "audio" in path.lower():
+                return "/openai/v1/audio/speech", {"type": "openai_audio"}
         elif method == "GET":
             if "model" in path.lower():
                 return "/openai/v1/models", {"type": "openai_models"}
@@ -161,6 +163,8 @@ class SmartRoutingMiddleware(BaseHTTPMiddleware):
                 return "/v1/embeddings", {"type": "v1_embeddings"}
             elif "image" in path.lower():
                 return "/v1/images/generations", {"type": "v1_images"}
+            elif "audio" in path.lower():
+                return "/v1/audio/speech", {"type": "v1_audio"}
         elif method == "GET":
             if "model" in path.lower():
                 return "/v1/models", {"type": "v1_models"}

app/router/openai_routes.py

@@ -1,4 +1,4 @@
-from fastapi import APIRouter, Depends, HTTPException
+from fastapi import APIRouter, Depends, HTTPException, Response
 from fastapi.responses import StreamingResponse
 
 from app.config.config import settings
@@ -7,6 +7,7 @@ from app.domain.openai_models import (
     ChatRequest,
     EmbeddingRequest,
     ImageGenerationRequest,
+    TTSRequest,
 )
 from app.handler.retry_handler import RetryHandler
 from app.handler.error_handler import handle_route_errors
@@ -14,6 +15,7 @@ from app.log.logger import get_openai_logger
 from app.service.chat.openai_chat_service import OpenAIChatService
 from app.service.embedding.embedding_service import EmbeddingService
 from app.service.image.image_create_service import ImageCreateService
+from app.service.tts.tts_service import TTSService
 from app.service.key.key_manager import KeyManager, get_key_manager_instance
 from app.service.model.model_service import ModelService
 
@@ -24,6 +26,7 @@ security_service = SecurityService()
 model_service = ModelService()
 embedding_service = EmbeddingService()
 image_create_service = ImageCreateService()
+tts_service = TTSService()
 
 
 async def get_key_manager():
@@ -41,6 +44,11 @@ async def get_openai_chat_service(key_manager: KeyManager = Depends(get_key_mana
     return OpenAIChatService(settings.BASE_URL, key_manager)
 
 
+async def get_tts_service():
+    """获取TTS服务实例"""
+    return tts_service
+
+
 @router.get("/v1/models")
 @router.get("/hf/v1/models")
 async def list_models(
@@ -147,3 +155,21 @@ async def get_keys_list(
             },
             "total": len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"]),
         }
+
+
+@router.post("/v1/audio/speech")
+@router.post("/hf/v1/audio/speech")
+async def text_to_speech(
+    request: TTSRequest,
+    _=Depends(security_service.verify_authorization),
+    api_key: str = Depends(get_next_working_key_wrapper),
+    tts_service: TTSService = Depends(get_tts_service),
+):
+    """处理 OpenAI TTS 请求。"""
+    operation_name = "text_to_speech"
+    async with handle_route_errors(logger, operation_name):
+        logger.info(f"Handling TTS request for model: {request.model}")
+        logger.debug(f"Request: \n{request.model_dump_json(indent=2)}")
+        logger.info(f"Using API key: {api_key}")
+        audio_data = await tts_service.create_tts(request, api_key)
+        return Response(content=audio_data, media_type="audio/wav")

app/service/tts/tts_service.py

@@ -0,0 +1,94 @@
+import datetime
+import io
+import re
+import time
+import wave
+from typing import Optional
+
+from google import genai
+
+from app.config.config import settings
+from app.database.services import add_error_log, add_request_log
+from app.domain.openai_models import TTSRequest
+from app.log.logger import get_openai_logger
+
+logger = get_openai_logger()
+
+
+def _create_wav_file(audio_data: bytes) -> bytes:
+    """Creates a WAV file in memory from raw audio data."""
+    with io.BytesIO() as wav_file:
+        with wave.open(wav_file, "wb") as wf:
+            wf.setnchannels(1)  # Mono
+            wf.setsampwidth(2)  # 16-bit
+            wf.setframerate(24000)  # 24kHz sample rate
+            wf.writeframes(audio_data)
+        return wav_file.getvalue()
+
+
+class TTSService:
+    async def create_tts(self, request: TTSRequest, api_key: str) -> Optional[bytes]:
+        """
+        使用 Google Gemini SDK 创建音频。
+        """
+        start_time = time.perf_counter()
+        request_datetime = datetime.datetime.now()
+        is_success = False
+        status_code = None
+        response = None
+        error_log_msg = ""
+        try:
+            client = genai.Client(api_key=api_key)
+            response =await client.aio.models.generate_content(
+                model=settings.TTS_MODEL,
+                contents=f"Speak in a {settings.TTS_SPEED} speed voice: {request.input}",
+                config={
+                    "response_modalities": ["Audio"],
+                    "speech_config": {
+                        "voice_config": {
+                            "prebuilt_voice_config": {
+                                "voice_name": settings.TTS_VOICE_NAME
+                            }
+                        }
+                    },
+                },
+            )
+            if (
+                response.candidates
+                and response.candidates[0].content.parts
+                and response.candidates[0].content.parts[0].inline_data
+            ):
+                raw_audio_data = response.candidates[0].content.parts[0].inline_data.data
+                is_success = True
+                status_code = 200
+                return _create_wav_file(raw_audio_data)
+        except Exception as e:
+            is_success = False
+            error_log_msg = f"Generic error: {e}"
+            logger.error(f"An error occurred in TTSService: {error_log_msg}")
+            match = re.search(r"status code (\d+)", str(e))
+            if match:
+                status_code = int(match.group(1))
+            else:
+                status_code = 500
+            raise
+        finally:
+            end_time = time.perf_counter()
+            latency_ms = int((end_time - start_time) * 1000)
+            if not is_success:
+                await add_error_log(
+                    gemini_key=api_key,
+                    model_name=settings.TTS_MODEL,
+                    error_type="google-tts",
+                    error_log=error_log_msg,
+                    error_code=status_code,
+                    request_msg=request.input
+                 )
+            await add_request_log(
+                model_name=settings.TTS_MODEL,
+                api_key=api_key,
+                is_success=is_success,
+                status_code=status_code,
+                latency_ms=latency_ms,
+                request_time=request_datetime
+            )

app/templates/config_editor.html

@@ -745,6 +745,13 @@ endblock %} {% block head_extra_styles %}
       >
         模型配置
       </button>
+      <button
+        class="tab-btn px-5 py-2 rounded-full font-medium text-sm transition-all duration-200"
+        data-tab="tts"
+        style="background-color: #f8fafc !important; color: #64748b !important; border: 2px solid #e2e8f0 !important; box-shadow: 0 1px 3px 0 rgba(0, 0, 0, 0.1) !important; font-weight: 500 !important;"
+      >
+        TTS 配置
+      </button>
       <button
         class="tab-btn px-5 py-2 rounded-full font-medium text-sm transition-all duration-200"
         data-tab="image"
@@ -1370,11 +1377,97 @@ endblock %} {% block head_extra_styles %}
           </div>
         </div>
       </div>
-
-      <!-- 图像生成相关配置 -->
-      <div class="config-section" id="image-section">
+ 
+       <!-- TTS配置 -->
+      <div class="config-section" id="tts-section">
         <h2
           class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
+        >
+          <i class="fas fa-volume-up text-violet-400"></i> TTS 相关配置
+        </h2>
+
+        <!-- TTS 模型 -->
+        <div class="mb-6">
+          <label for="TTS_MODEL" class="block font-semibold mb-2 text-gray-700"
+            >TTS 模型</label
+          >
+          <select
+            id="TTS_MODEL"
+            name="TTS_MODEL"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="gemini-2.5-flash-preview-tts">gemini-2.5-flash-preview-tts</option>
+            <option value="gemini-2.5-pro-preview-tts">gemini-2.5-pro-preview-tts</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">用于TTS的模型</small>
+        </div>
+
+        <!-- TTS 语音名称 -->
+        <div class="mb-6">
+          <label for="TTS_VOICE_NAME" class="block font-semibold mb-2 text-gray-700"
+            >TTS 语音名称</label
+          >
+          <select
+            id="TTS_VOICE_NAME"
+            name="TTS_VOICE_NAME"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="Zephyr">Zephyr (明亮)</option>
+            <option value="Puck">Puck (欢快)</option>
+            <option value="Charon">Charon (信息丰富)</option>
+            <option value="Kore">Kore (坚定)</option>
+            <option value="Fenrir">Fenrir (易激动)</option>
+            <option value="Leda">Leda (年轻)</option>
+            <option value="Orus">Orus (坚定)</option>
+            <option value="Aoede">Aoede (轻松)</option>
+            <option value="Callirhoe">Callirhoe (随和)</option>
+            <option value="Autonoe">Autonoe (明亮)</option>
+            <option value="Enceladus">Enceladus (呼吸感)</option>
+            <option value="Iapetus">Iapetus (清晰)</option>
+            <option value="Umbriel">Umbriel (随和)</option>
+            <option value="Algieba">Algieba (平滑)</option>
+            <option value="Despina">Despina (平滑)</option>
+            <option value="Erinome">Erinome (清晰)</option>
+            <option value="Algenib">Algenib (沙哑)</option>
+            <option value="Rasalgethi">Rasalgethi (信息丰富)</option>
+            <option value="Laomedeia">Laomedeia (欢快)</option>
+            <option value="Achernar">Achernar (轻柔)</option>
+            <option value="Alnilam">Alnilam (坚定)</option>
+            <option value="Schedar">Schedar (平稳)</option>
+            <option value="Gacrux">Gacrux (成熟)</option>
+            <option value="Pulcherrima">Pulcherrima (向前)</option>
+            <option value="Achird">Achird (友好)</option>
+            <option value="Zubenelgenubi">Zubenelgenubi (休闲)</option>
+            <option value="Vindemiatrix">Vindemiatrix (温柔)</option>
+            <option value="Sadachbia">Sadachbia (活泼)</option>
+            <option value="Sadaltager">Sadaltager (博学)</option>
+            <option value="Sulafat">Sulafat (温暖)</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">TTS 的语音名称，控制风格、语调、口音和节奏</small>
+        </div>
+
+        <!-- TTS 语速 -->
+        <div class="mb-6">
+          <label for="TTS_SPEED" class="block font-semibold mb-2 text-gray-700"
+            >TTS 语速</label
+          >
+          <select
+            id="TTS_SPEED"
+            name="TTS_SPEED"
+            class="w-full px-4 py-3 rounded-lg form-select-themed"
+          >
+            <option value="slow">慢</option>
+            <option value="normal">正常</option>
+            <option value="fast">快</option>
+          </select>
+          <small class="text-gray-500 mt-1 block">选择 TTS 的语速</small>
+        </div>
+      </div>
+
+       <!-- 图像生成相关配置 -->
+       <div class="config-section" id="image-section">
+         <h2
+          class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
         >
           <i class="fas fa-image text-violet-400"></i> 图像生成配置
         </h2>
@@ -1511,12 +1604,12 @@ endblock %} {% block head_extra_styles %}
         </div>
       </div>
 
-      <!-- 流式输出优化器配置 -->
+      <!-- 流式输出优化配置 -->
       <div class="config-section" id="stream-section">
         <h2
           class="text-xl font-bold mb-6 pb-3 border-b flex items-center gap-2 text-gray-800 border-violet-300 border-opacity-30"
         >
-          <i class="fas fa-stream text-violet-400"></i> 流式输出优化器
+          <i class="fas fa-stream text-violet-400"></i> 流式输出相关配置
         </h2>
 
         <!-- 启用流式输出优化 -->