feat: Add MiniMax TTS API provider

astrbot/core/config/default.py

@@ -788,6 +788,25 @@ CONFIG_METADATA_2 = {
                         "azure_tts_subscription_key": "",
                         "azure_tts_region": "eastus"
                     },
+                    "MiniMax TTS(API)": {
+                        "id": "minimax_tts",
+                        "type": "minimax_tts_api",
+                        "provider_type": "text_to_speech",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "https://api.minimax.chat/v1/t2a_v2",
+                        "minimax-group-id": "",
+                        "model": "speech-02-turbo",
+                        "minimax-langboost": "auto",
+                        "minimax-voice-speed": 1.0,
+                        "minimax-voice-vol": 1.0,
+                        "minimax-voice-pitch": 0,
+                        "minimax-voice-id": "female-shaonv",
+                        "minimax-voice-emotion": "neutral",
+                        "minimax-voice-latex": False,
+                        "minimax-voice-english-normalization": False,
+                        "timeout": "20",
+                    },
                 },
                 "items": {
                     "azure_tts_voice": {
@@ -911,6 +930,53 @@ CONFIG_METADATA_2 = {
                             },
                         },
                     },
+                    "minimax-group-id": {
+                        "type": "string",
+                        "description": "用户所属的组",
+                        "hint": "于账户管理->基本信息中可见",
+                    },
+                    "minimax-langboost": {
+                        "type": "string",
+                        "description": "指定语言/方言识别能力",
+                        "hint": "增强对指定的小语种和方言的识别能力，设置后可以提升在指定小语种/方言场景下的语音表现",
+                        "options": [ "Chinese","Chinese,Yue","English","Arabic","Russian","Spanish","French","Portuguese","German","Turkish","Dutch","Ukrainian","Vietnamese","Indonesian","Japanese","Italian","Korean","Thai","Polish","Romanian","Greek","Czech","Finnish","Hindi","auto",],
+                    },
+                    "minimax-voice-speed": {
+                        "type": "float",
+                        "description": "语速取值越大，语速越快",
+                        "hint": "生成声音的语速, 取值[0.5, 2], 默认为1.0, 取值越大，语速越快",
+                    },
+                    "minimax-voice-vol": {
+                        "type": "float",
+                        "description": "音量",
+                        "hint": "生成声音的音量, 取值(0, 10], 默认为1.0, 取值越大，音量越高",
+                    },
+                    "minimax-voice-pitch": {
+                        "type": "int",
+                        "description": "语调",
+                        "hint": "生成声音的语调, 取值[-12, 12], 默认为0",
+                    },
+                    "minimax-voice-id": {
+                        "type": "string",
+                        "description": "音色编号",
+                        "hint": "请求的音色编号, 请见官网文档",
+                    },
+                    "minimax-voice-emotion": {
+                        "type": "string",
+                        "description": "语音情绪",
+                        "hint": "控制合成语音的情绪",
+                        "options": ["happy","sad","angry","fearful","disgusted","surprised","neutral",],
+                    },
+                    "minimax-voice-latex": {
+                        "type": "bool",
+                        "description": "是否支持朗读latex公式",
+                        "hint": "",
+                    },
+                    "minimax-voice-english-normalization": {
+                        "type": "bool",
+                        "description": "是否支持英语文本规范化",
+                        "hint": "可提升数字阅读场景的性能，但会略微增加延迟",
+                    },
                     "rag_options": {
                         "description": "RAG 选项",
                         "type": "object",

astrbot/core/provider/manager.py

@@ -206,6 +206,10 @@ class ProviderManager:
                     from .sources.azure_tts_source import (
                         AzureTTSProvider as AzureTTSProvider,
                     )
+                case "minimax_tts_api":
+                    from .sources.minimax_tts_api_source import (
+                        ProviderMiniMaxTTSAPI as ProviderMiniMaxTTSAPI,
+                    )
         except (ImportError, ModuleNotFoundError) as e:
             logger.critical(
                 f"加载 {provider_config['type']}({provider_config['id']}) 提供商适配器失败：{e}。可能是因为有未安装的依赖。"

astrbot/core/provider/sources/minimax_tts_api_source.py

@@ -0,0 +1,120 @@
+import json
+import os
+import uuid
+from typing import Iterator
+
+import requests
+
+from astrbot.core.utils.astrbot_path import get_astrbot_data_path
+
+from ..entities import ProviderType
+from ..provider import TTSProvider
+from ..register import register_provider_adapter
+
+
+@register_provider_adapter(
+    "minimax_tts_api", "MiniMax TTS API", provider_type=ProviderType.TEXT_TO_SPEECH
+)
+class ProviderMiniMaxTTSAPI(TTSProvider):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key: str = provider_config.get("api_key", "")
+        self.api_base: str = provider_config.get(
+            "api_base", "https://api.minimax.chat/v1/t2a_v2"
+        )
+        self.group_id: str = provider_config.get("minimax-group-id", "")
+        self.set_model(provider_config.get("model", ""))
+        self.lang_boost: str = provider_config.get("minimax-langboost", "auto")
+
+        self.voice_setting: dict = {
+            "speed": provider_config.get("minimax-voice-speed", 1.0),
+            "vol": provider_config.get("minimax-voice-vol", 1.0),
+            "pitch": provider_config.get("minimax-voice-pitch", 0),
+            "voice_id": provider_config.get("minimax-voice-id", ""),
+            "emotion": provider_config.get("minimax-voice-emotion", "neutral"),
+            "latex_read": provider_config.get("minimax-voice-latex", False),
+            "english_normalization": provider_config.get(
+                "minimax-voice-english-normalization", False
+            ),
+        }
+
+        self.audio_setting: dict = {
+            "sample_rate": 32000,
+            "bitrate": 128000,
+            "format": "mp3",
+        }
+
+        self.concat_base_url: str = self.api_base + "?GroupId=" + self.group_id
+        self.headers = {
+            "Authorization": f"Bearer {self.chosen_api_key}",
+            "accept": "application/json, text/plain, */*",
+            "content-type": "application/json",
+        }
+
+    def _build_tts_stream_body(self, text: str):
+        """构建流式请求体"""
+        body = json.dumps(
+            {
+                "model": self.model_name,
+                "text": text,
+                "stream": True,
+                "language_boost": self.lang_boost,
+                "voice_setting": self.voice_setting,
+                "audio_setting": self.audio_setting,
+            }
+        )
+        return body
+
+    def _call_tts_stream(self, text: str) -> Iterator[bytes]:
+        """进行流式请求"""
+        tts_body = self._build_tts_stream_body(text)
+        try:
+            response = requests.request(
+                "POST",
+                self.concat_base_url,
+                stream=True,
+                headers=self.headers,
+                data=tts_body,
+            )
+            response.raise_for_status()
+            for chunk in response.raw:
+                if chunk:
+                    if chunk[:5] == b"data:":
+                        data = json.loads(chunk[5:])
+                        if "data" in data and "extra_info" not in data:
+                            if "audio" in data["data"]:
+                                audio = data["data"]["audio"]
+                                yield audio
+        except requests.exceptions.RequestException as e:
+            raise Exception(f"MiniMax TTS API请求失败: {str(e)}")
+
+    def _audio_play(self, audio_stream: Iterator[bytes]) -> bytes:
+        """解码数据流到audio比特流"""
+        audio = b""
+        for chunk in audio_stream:
+            if chunk is not None and chunk != "\n":
+                decoded_hex = bytes.fromhex(chunk)
+                audio += decoded_hex
+
+        return audio
+
+    async def get_audio(self, text: str) -> str:
+        temp_dir = os.path.join(get_astrbot_data_path(), "temp")
+        path = os.path.join(temp_dir, f"minimax_tts_api_{uuid.uuid4()}.mp3")
+
+        try:
+            audio_chunk_iterator = self._call_tts_stream(text)
+            audio = self._audio_play(audio_chunk_iterator)
+
+            # 结果保存至文件
+            with open(path, "wb") as file:
+                file.write(audio)
+
+            return path
+
+        except requests.exceptions.RequestException as e:
+            raise e

dashboard/src/views/ProviderPage.vue

@@ -30,7 +30,7 @@
         <v-card-text class="px-4 py-3">
           <item-card-grid
             :items="config_data.provider || []"
-            title-field="id" 
+            title-field="id"
             enabled-field="enable"
             empty-icon="mdi-api-off"
             empty-text="暂无服务提供商，点击 新增服务提供商 添加"
@@ -42,7 +42,7 @@
               <div class="d-flex align-center mb-2">
                 <v-icon size="small" color="grey" class="me-2">mdi-tag</v-icon>
                 <span class="text-caption text-medium-emphasis">
-                  提供商类型: 
+                  提供商类型:
                   <v-chip size="x-small" color="primary" class="ml-1">{{ item.type }}</v-chip>
                 </span>
               </div>
@@ -94,7 +94,7 @@
             <v-icon>mdi-close</v-icon>
           </v-btn>
         </v-card-title>
-        
+
         <v-card-text class="pa-4" style="overflow-y: auto;">
           <v-tabs v-model="activeProviderTab" grow slider-color="primary" bg-color="background">
             <v-tab value="chat_completion" class="font-weight-medium px-3">
@@ -110,14 +110,14 @@
               文字转语音
             </v-tab>
           </v-tabs>
-          
+
           <v-window v-model="activeProviderTab" class="mt-4">
-            <v-window-item v-for="tabType in ['chat_completion', 'speech_to_text', 'text_to_speech']" 
-                          :key="tabType" 
+            <v-window-item v-for="tabType in ['chat_completion', 'speech_to_text', 'text_to_speech']"
+                          :key="tabType"
                           :value="tabType">
               <v-row class="mt-1">
-                <v-col v-for="(template, name) in getTemplatesByType(tabType)" 
-                      :key="name" 
+                <v-col v-for="(template, name) in getTemplatesByType(tabType)"
+                      :key="name"
                       cols="12" sm="6" md="4">
                   <v-card variant="outlined" hover class="provider-card" @click="selectProviderTemplate(name)">
                     <v-card-item>
@@ -155,17 +155,17 @@
           <v-icon color="white" class="me-2">{{ updatingMode ? 'mdi-pencil' : 'mdi-plus' }}</v-icon>
           <span>{{ updatingMode ? '编辑' : '新增' }} {{ newSelectedProviderName }} 服务提供商</span>
         </v-card-title>
-        
+
         <v-card-text class="py-4">
-          <AstrBotConfig 
+          <AstrBotConfig
             :iterable="newSelectedProviderConfig"
             :metadata="metadata['provider_group']?.metadata"
-            metadataKey="provider" 
+            metadataKey="provider"
           />
         </v-card-text>
-        
+
         <v-divider></v-divider>
-        
+
         <v-card-actions class="pa-4">
           <v-spacer></v-spacer>
           <v-btn variant="text" @click="showProviderCfg = false" :disabled="loading">
@@ -183,7 +183,7 @@
       location="top">
       {{ save_message }}
     </v-snackbar>
-    
+
     <WaitingForRestart ref="wfr"></WaitingForRestart>
   </div>
 </template>
@@ -221,7 +221,7 @@ export default {
       save_message_success: "success",
 
       showConsole: false,
-      
+
       // 新增提供商对话框相关
       showAddProviderDialog: false,
       activeProviderTab: 'chat_completion',
@@ -247,16 +247,16 @@ export default {
     getTemplatesByType(type) {
       const templates = this.metadata['provider_group']?.metadata?.provider?.config_template || {};
       const filtered = {};
-      
+
       for (const [name, template] of Object.entries(templates)) {
         if (template.provider_type === type) {
           filtered[name] = template;
         }
       }
-      
+
       return filtered;
     },
-    
+
     // 获取提供商类型对应的图标
     getProviderIcon(type) {
       const icons = {
@@ -278,6 +278,7 @@ export default {
         'LM Studio': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/lmstudio.svg',
         'FishAudio': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/fishaudio.svg',
         'Azure': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/azure.svg',
+        'MiniMax': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/minimax.svg',
       };
       for (const key in icons) {
         if (type.startsWith(key)) {
@@ -296,7 +297,7 @@ export default {
       };
       return names[tabType] || tabType;
     },
-    
+
     // 获取提供商简介
     getProviderDescription(template, name) {
       if (name == 'OpenAI') {
@@ -304,7 +305,7 @@ export default {
       }
       return `${template.type} 服务提供商`;
     },
-    
+
     // 选择提供商模板
     selectProviderTemplate(name) {
       this.newSelectedProviderName = name;
@@ -334,7 +335,7 @@ export default {
           break;
         }
       }
-      
+
       const mergeConfigWithOrder = (target, source, reference) => {
         // 首先复制所有source中的属性到target
         if (source && typeof source === 'object' && !Array.isArray(source)) {
@@ -348,7 +349,7 @@ export default {
             }
           }
         }
-        
+
         // 然后根据reference的结构添加或覆盖属性
         for (let key in reference) {
           if (typeof reference[key] === 'object' && reference[key] !== null) {
@@ -356,8 +357,8 @@ export default {
               target[key] = Array.isArray(reference[key]) ? [] : {};
             }
             mergeConfigWithOrder(
-              target[key], 
-              source && source[key] ? source[key] : {}, 
+              target[key],
+              source && source[key] ? source[key] : {},
               reference[key]
             );
           } else if (!(key in target)) {
@@ -366,7 +367,7 @@ export default {
           }
         }
       };
-      
+
       if (defaultConfig) {
         mergeConfigWithOrder(this.newSelectedProviderConfig, provider, defaultConfig);
       }
@@ -417,7 +418,7 @@ export default {
 
     providerStatusChange(provider) {
       provider.enable = !provider.enable; // 切换状态
-      
+
       axios.post('/api/config/provider/update', {
         id: provider.id,
         config: provider
@@ -429,13 +430,13 @@ export default {
         this.showError(err.response?.data?.message || err.message);
       });
     },
-    
+
     showSuccess(message) {
       this.save_message = message;
       this.save_message_success = "success";
       this.save_message_snack = true;
     },
-    
+
     showError(message) {
       this.save_message = message;
       this.save_message_success = "error";
@@ -475,4 +476,4 @@ export default {
 .v-window {
   border-radius: 4px;
 }
-</style>
+</style>