feat: add and expand MiniMax provider support

.env.example

@@ -33,7 +33,9 @@ KIMI_BASE_URL=
 KIMI_MODELS=
 
 MINIMAX_API_KEY=
-MINIMAX_BASE_URL=
+# MiniMax Anthropic-compatible endpoint for the built-in Anthropic SDK integration
+MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic/v1
+# Example: MiniMax-M2.7,MiniMax-M2.7-highspeed,MiniMax-M2.5,MiniMax-M2.1
 MINIMAX_MODELS=
 
 GLM_API_KEY=
@@ -66,6 +68,9 @@ TTS_GLM_BASE_URL=
 TTS_QWEN_API_KEY=
 TTS_QWEN_BASE_URL=
 
+TTS_MINIMAX_API_KEY=
+# MiniMax TTS endpoint (speech-2.8 / 2.6 / 02 / 01 series)
+TTS_MINIMAX_BASE_URL=https://api.minimaxi.com
 TTS_ELEVENLABS_API_KEY=
 TTS_ELEVENLABS_BASE_URL=
 
@@ -96,6 +101,10 @@ IMAGE_QWEN_IMAGE_BASE_URL=
 IMAGE_NANO_BANANA_API_KEY=
 IMAGE_NANO_BANANA_BASE_URL=
 
+IMAGE_MINIMAX_API_KEY=
+# Example models: image-01, image-01-live
+IMAGE_MINIMAX_BASE_URL=https://api.minimaxi.com
+
 IMAGE_GROK_API_KEY=
 IMAGE_GROK_BASE_URL=
 
@@ -113,6 +122,10 @@ VIDEO_VEO_BASE_URL=
 VIDEO_SORA_API_KEY=
 VIDEO_SORA_BASE_URL=
 
+VIDEO_MINIMAX_API_KEY=
+# Example models: MiniMax-Hailuo-2.3, MiniMax-Hailuo-2.3-Fast, MiniMax-Hailuo-02
+VIDEO_MINIMAX_BASE_URL=https://api.minimaxi.com
+
 VIDEO_GROK_API_KEY=
 VIDEO_GROK_BASE_URL=
 
@@ -132,6 +145,7 @@ TAVILY_API_KEY=
 
 # Optional server-side default model for API routes like /api/generate-classroom
 # Example: anthropic:claude-3-5-haiku-20241022 or google:gemini-3-flash-preview
+# MiniMax example: minimax:MiniMax-M2.7-highspeed
 DEFAULT_MODEL=
 
 # LOG_LEVEL=info

README-zh.md

@@ -114,11 +114,30 @@ providers:
     apiKey: sk-ant-...
 ```
 
-支持的服务商：**OpenAI**、**Anthropic**、**Google Gemini**、**DeepSeek**、**Grok (xAI)** 以及任何兼容 OpenAI API 的服务。
+支持的服务商：**OpenAI**、**Anthropic**、**Google Gemini**、**DeepSeek**、**MiniMax**、**Grok (xAI)** 以及任何兼容 OpenAI API 的服务。
+
+MiniMax 快速示例：
+
+```env
+MINIMAX_API_KEY=...
+MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic/v1
+DEFAULT_MODEL=minimax:MiniMax-M2.7-highspeed
+
+TTS_MINIMAX_API_KEY=...
+TTS_MINIMAX_BASE_URL=https://api.minimaxi.com
+
+IMAGE_MINIMAX_API_KEY=...
+IMAGE_MINIMAX_BASE_URL=https://api.minimaxi.com
+
+VIDEO_MINIMAX_API_KEY=...
+VIDEO_MINIMAX_BASE_URL=https://api.minimaxi.com
+```
 
 > **推荐模型：** **Gemini 3 Flash** — 效果与速度的最佳平衡。追求最高质量可选 **Gemini 3.1 Pro**（速度较慢）。
 >
 > 如果希望 OpenMAIC 服务端默认走 Gemini，还需要额外设置 `DEFAULT_MODEL=google:gemini-3-flash-preview`。
+>
+> 如果希望默认走 MiniMax，可设置 `DEFAULT_MODEL=minimax:MiniMax-M2.7-highspeed`。
 
 ### 3. 启动
 

README.md

@@ -114,11 +114,30 @@ providers:
     apiKey: sk-ant-...
 ```
 
-Supported providers: **OpenAI**, **Anthropic**, **Google Gemini**, **DeepSeek**, **Grok (xAI)**, and any OpenAI-compatible API.
+Supported providers: **OpenAI**, **Anthropic**, **Google Gemini**, **DeepSeek**, **MiniMax**, **Grok (xAI)**, and any OpenAI-compatible API.
+
+MiniMax quick examples:
+
+```env
+MINIMAX_API_KEY=...
+MINIMAX_BASE_URL=https://api.minimaxi.com/anthropic/v1
+DEFAULT_MODEL=minimax:MiniMax-M2.7-highspeed
+
+TTS_MINIMAX_API_KEY=...
+TTS_MINIMAX_BASE_URL=https://api.minimaxi.com
+
+IMAGE_MINIMAX_API_KEY=...
+IMAGE_MINIMAX_BASE_URL=https://api.minimaxi.com
+
+VIDEO_MINIMAX_API_KEY=...
+VIDEO_MINIMAX_BASE_URL=https://api.minimaxi.com
+```
 
 > **Recommended model:** **Gemini 3 Flash** — best balance of quality and speed. For highest quality (at slower speed), try **Gemini 3.1 Pro**.
 >
 > If you want OpenMAIC server APIs to use Gemini by default, also set `DEFAULT_MODEL=google:gemini-3-flash-preview`.
+>
+> If you want to use MiniMax as the default server model, set `DEFAULT_MODEL=minimax:MiniMax-M2.7-highspeed`.
 
 ### 3. Run
 
@@ -483,3 +502,4 @@ If you find OpenMAIC useful in your research, please consider citing:
 ## 📄 License
 
 This project is licensed under the [GNU Affero General Public License v3.0](LICENSE).
+

app/api/generate/tts/route.ts

@@ -22,15 +22,17 @@ export const maxDuration = 30;
 export async function POST(req: NextRequest) {
   try {
     const body = await req.json();
-    const { text, audioId, ttsProviderId, ttsVoice, ttsSpeed, ttsApiKey, ttsBaseUrl } = body as {
-      text: string;
-      audioId: string;
-      ttsProviderId: TTSProviderId;
-      ttsVoice: string;
-      ttsSpeed?: number;
-      ttsApiKey?: string;
-      ttsBaseUrl?: string;
-    };
+    const { text, audioId, ttsProviderId, ttsVoice, ttsSpeed, ttsModel, ttsApiKey, ttsBaseUrl } =
+      body as {
+        text: string;
+        audioId: string;
+        ttsProviderId: TTSProviderId;
+        ttsVoice: string;
+        ttsSpeed?: number;
+        ttsModel?: string;
+        ttsApiKey?: string;
+        ttsBaseUrl?: string;
+      };
 
     // Validate required fields
     if (!text || !audioId || !ttsProviderId || !ttsVoice) {
@@ -66,12 +68,13 @@ export async function POST(req: NextRequest) {
       providerId: ttsProviderId,
       voice: ttsVoice,
       speed: ttsSpeed ?? 1.0,
+      model: ttsModel,
       apiKey,
       baseUrl,
     };
 
     log.info(
-      `Generating TTS: provider=${ttsProviderId}, voice=${ttsVoice}, audioId=${audioId}, textLen=${text.length}`,
+      `Generating TTS: provider=${ttsProviderId}, model=${ttsModel || 'default'}, voice=${ttsVoice}, audioId=${audioId}, textLen=${text.length}`,
     );
 
     // Generate audio

components/generation/media-popover.tsx

@@ -9,8 +9,8 @@
   Mic,
   SlidersHorizontal,
   ChevronRight,
   Play,
   Loader2,
 } from 'lucide-react';
 import { toast } from 'sonner';
 import { Popover, PopoverContent, PopoverTrigger } from '@/components/ui/popover';
@@ -24,7 +24,7 @@
   SelectTrigger,
   SelectValue,
 } from '@/components/ui/select';
 import { Slider } from '@/components/ui/slider';
 import { Switch } from '@/components/ui/switch';
 import { cn } from '@/lib/utils';
 import { useI18n } from '@/lib/hooks/use-i18n';
@@ -90,6 +90,7 @@
     'qwen-tts': t('settings.providerQwenTTS'),
     'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
+    'minimax-tts': t('settings.providerMiniMaxTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };
   return names[providerId] || providerId;
@@ -136,9 +137,9 @@
   const ttsVoice = useSettingsStore((s) => s.ttsVoice);
   const ttsSpeed = useSettingsStore((s) => s.ttsSpeed);
   const ttsProvidersConfig = useSettingsStore((s) => s.ttsProvidersConfig);
   const setTTSProvider = useSettingsStore((s) => s.setTTSProvider);
   const setTTSVoice = useSettingsStore((s) => s.setTTSVoice);
   const setTTSSpeed = useSettingsStore((s) => s.setTTSSpeed);
 
   const asrProviderId = useSettingsStore((s) => s.asrProviderId);
   const asrLanguage = useSettingsStore((s) => s.asrLanguage);
@@ -166,7 +167,7 @@
     needsKey: boolean,
   ) => !needsKey || !!configs[id]?.apiKey || !!configs[id]?.isServerConfigured;
 
   const ttsSpeedRange = TTS_PROVIDERS[ttsProviderId]?.speedRange;
 
   // ─── Dynamic browser voices ───
   const [browserVoices, setBrowserVoices] = useState<SpeechSynthesisVoice[]>([]);
@@ -215,7 +216,7 @@
 
   // TTS: grouped by provider, voices as items (matching Image/Video pattern)
   // Browser-native voices are split into sub-groups by language.
   const ttsGroups = useMemo(() => {
     const groups: SelectGroupData[] = [];
 
     for (const p of Object.values(TTS_PROVIDERS)) {
@@ -260,7 +261,7 @@
   }, [ttsProvidersConfig, locale, browserVoices, t]);
 
   // TTS preview
   const handlePreview = useCallback(async () => {
     if (previewing) {
       stopPreview();
       return;
@@ -274,6 +275,7 @@
         speed: ttsSpeed,
         apiKey: providerConfig?.apiKey,
         baseUrl: providerConfig?.baseUrl,
+        model: providerConfig?.model,
       });
     } catch (error) {
       const message =

components/settings/audio-settings.tsx

@@ -16,6 +16,7 @@ import { useI18n } from '@/lib/hooks/use-i18n';
 import { useSettingsStore } from '@/lib/store/settings';
 import {
   TTS_PROVIDERS,
+  MINIMAX_TTS_MODELS,
   getTTSVoices,
   ASR_PROVIDERS,
   getASRSupportedLanguages,
@@ -39,6 +40,7 @@ function getTTSProviderName(providerId: TTSProviderId, t: (key: string) => strin
     'qwen-tts': t('settings.providerQwenTTS'),
     'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
+    'minimax-tts': t('settings.providerMiniMaxTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };
   return names[providerId];
@@ -101,7 +103,7 @@ export function AudioSettings({ onSave }: AudioSettingsProps = {}) {
 
   const handleTTSProviderConfigChange = (
     providerId: TTSProviderId,
-    config: Partial<{ apiKey: string; baseUrl: string; enabled: boolean }>,
+    config: Partial<{ apiKey: string; baseUrl: string; model?: string; enabled: boolean }>,
   ) => {
     setTTSProviderConfig(providerId, config);
     onSave?.();
@@ -452,49 +454,76 @@ export function AudioSettings({ onSave }: AudioSettingsProps = {}) {
 
           {(ttsProvider.requiresApiKey ||
             ttsProvidersConfig[ttsProviderId]?.isServerConfigured) && (
-            <div className="grid grid-cols-2 gap-4">
-              <div className="space-y-2">
-                <Label className="text-sm">{t('settings.ttsApiKey')}</Label>
-                <div className="relative">
+            <>
+              <div className="grid grid-cols-2 gap-4">
+                <div className="space-y-2">
+                  <Label className="text-sm">{t('settings.ttsApiKey')}</Label>
+                  <div className="relative">
+                    <Input
+                      type={showTTSApiKey ? 'text' : 'password'}
+                      placeholder={
+                        ttsProvidersConfig[ttsProviderId]?.isServerConfigured
+                          ? t('settings.optionalOverride')
+                          : t('settings.enterApiKey')
+                      }
+                      value={ttsProvidersConfig[ttsProviderId]?.apiKey || ''}
+                      onChange={(e) =>
+                        handleTTSProviderConfigChange(ttsProviderId, {
+                          apiKey: e.target.value,
+                        })
+                      }
+                      className="font-mono text-sm pr-10"
+                    />
+                    <button
+                      type="button"
+                      onClick={() => setShowTTSApiKey(!showTTSApiKey)}
+                      className="absolute right-2 top-1/2 -translate-y-1/2 text-muted-foreground hover:text-foreground"
+                    >
+                      {showTTSApiKey ? <EyeOff className="h-4 w-4" /> : <Eye className="h-4 w-4" />}
+                    </button>
+                  </div>
+                </div>
+
+                <div className="space-y-2">
+                  <Label className="text-sm">{t('settings.ttsBaseUrl')}</Label>
                   <Input
-                    type={showTTSApiKey ? 'text' : 'password'}
-                    placeholder={
-                      ttsProvidersConfig[ttsProviderId]?.isServerConfigured
-                        ? t('settings.optionalOverride')
-                        : t('settings.enterApiKey')
-                    }
-                    value={ttsProvidersConfig[ttsProviderId]?.apiKey || ''}
+                    placeholder={ttsProvider.defaultBaseUrl || t('settings.enterCustomBaseUrl')}
+                    value={ttsProvidersConfig[ttsProviderId]?.baseUrl || ''}
                     onChange={(e) =>
                       handleTTSProviderConfigChange(ttsProviderId, {
-                        apiKey: e.target.value,
+                        baseUrl: e.target.value,
                       })
                     }
-                    className="font-mono text-sm pr-10"
+                    className="text-sm"
                   />
-                  <button
-                    type="button"
-                    onClick={() => setShowTTSApiKey(!showTTSApiKey)}
-                    className="absolute right-2 top-1/2 -translate-y-1/2 text-muted-foreground hover:text-foreground"
-                  >
-                    {showTTSApiKey ? <EyeOff className="h-4 w-4" /> : <Eye className="h-4 w-4" />}
-                  </button>
                 </div>
               </div>
 
-              <div className="space-y-2">
-                <Label className="text-sm">{t('settings.ttsBaseUrl')}</Label>
-                <Input
-                  placeholder={ttsProvider.defaultBaseUrl || t('settings.enterCustomBaseUrl')}
-                  value={ttsProvidersConfig[ttsProviderId]?.baseUrl || ''}
-                  onChange={(e) =>
-                    handleTTSProviderConfigChange(ttsProviderId, {
-                      baseUrl: e.target.value,
-                    })
-                  }
-                  className="text-sm"
-                />
-              </div>
-            </div>
+              {ttsProviderId === 'minimax-tts' && (
+                <div className="space-y-2">
+                  <Label className="text-sm">{t('settings.ttsModel')}</Label>
+                  <Select
+                    value={ttsProvidersConfig[ttsProviderId]?.model || 'speech-2.8-turbo'}
+                    onValueChange={(value) =>
+                      handleTTSProviderConfigChange(ttsProviderId, {
+                        model: value,
+                      })
+                    }
+                  >
+                    <SelectTrigger>
+                      <SelectValue placeholder={t('settings.ttsModelPlaceholder')} />
+                    </SelectTrigger>
+                    <SelectContent>
+                      {MINIMAX_TTS_MODELS.map((model) => (
+                        <SelectItem key={model.id} value={model.id}>
+                          {model.name}
+                        </SelectItem>
+                      ))}
+                    </SelectContent>
+                  </Select>
+                </div>
+              )}
+            </>
           )}
         </div>
       </div>

components/settings/index.tsx

@@ -123,6 +123,7 @@ function getTTSProviderName(providerId: TTSProviderId, t: (key: string) => strin
     'qwen-tts': t('settings.providerQwenTTS'),
     'doubao-tts': t('settings.providerDoubaoTTS'),
     'elevenlabs-tts': t('settings.providerElevenLabsTTS'),
+    'minimax-tts': t('settings.providerMiniMaxTTS'),
     'browser-native-tts': t('settings.providerBrowserNativeTTS'),
   };
   return names[providerId];
@@ -142,13 +143,15 @@ const IMAGE_PROVIDER_NAMES: Record<ImageProviderId, string> = {
   seedream: 'providerSeedream',
   'qwen-image': 'providerQwenImage',
   'nano-banana': 'providerNanoBanana',
+  'minimax-image': 'providerMiniMaxImage',
   'grok-image': 'providerGrokImage',
 };
 
 const IMAGE_PROVIDER_ICONS: Record<ImageProviderId, string> = {
   seedream: '/logos/doubao.svg',
   'qwen-image': '/logos/bailian.svg',
   'nano-banana': '/logos/gemini.svg',
+  'minimax-image': '/logos/minimax.svg',
   'grok-image': '/logos/grok.svg',
 };
 
@@ -157,6 +160,7 @@ const VIDEO_PROVIDER_NAMES: Record<VideoProviderId, string> = {
   kling: 'providerKling',
   veo: 'providerVeo',
   sora: 'providerSora',
+  'minimax-video': 'providerMiniMaxVideo',
   'grok-video': 'providerGrokVideo',
 };
 
@@ -165,6 +169,7 @@ const VIDEO_PROVIDER_ICONS: Record<VideoProviderId, string> = {
   kling: '/logos/kling.svg',
   veo: '/logos/gemini.svg',
   sora: '/logos/openai.svg',
+  'minimax-video': '/logos/minimax.svg',
   'grok-video': '/logos/grok.svg',
 };