diff --git a/extensions/xiaomi/speech-provider.test.ts b/extensions/xiaomi/speech-provider.test.ts
index 8d14845b4d4..6f7a45d43c3 100644
--- a/extensions/xiaomi/speech-provider.test.ts
+++ b/extensions/xiaomi/speech-provider.test.ts
@@ -82,6 +82,24 @@ describe("buildXiaomiSpeechProvider", () => {
       });
       expect(config.voice).toBe("default_zh");
     });
+
+    it("accepts generic model and speaker voice aliases", () => {
+      const config = provider.resolveConfig!({
+        rawConfig: {
+          providers: {
+            xiaomi: {
+              modelId: "mimo-v2.5-tts-voicedesign",
+              speakerVoice: "Chloe",
+            },
+          },
+        },
+        cfg: {} as never,
+        timeoutMs: 30000,
+      });
+
+      expect(config.model).toBe("mimo-v2.5-tts-voicedesign");
+      expect(config.voice).toBe("Chloe");
+    });
   });
 
   describe("parseDirectiveToken", () => {
@@ -195,8 +213,8 @@ describe("buildXiaomiSpeechProvider", () => {
         cfg: {} as never,
         providerConfig: {
           apiKey: "sk-test",
-          model: "mimo-v2.5-tts-voicedesign",
-          voice: "Chloe",
+          modelId: "mimo-v2.5-tts-voicedesign",
+          speakerVoice: "Chloe",
           format: "wav",
           style: "Warm, bright, natural voice.",
         },
diff --git a/extensions/xiaomi/speech-provider.ts b/extensions/xiaomi/speech-provider.ts
index f589a56557f..f9bf7833bb3 100644
--- a/extensions/xiaomi/speech-provider.ts
+++ b/extensions/xiaomi/speech-provider.ts
@@ -22,11 +22,7 @@ const XIAOMI_TTS_VOICE_DESIGN_MODEL = "mimo-v2.5-tts-voicedesign";
 const DEFAULT_XIAOMI_TTS_VOICE_DESIGN_STYLE =
   "Warm, natural, and friendly voice with clear pronunciation and conversational pacing.";
 
-const XIAOMI_TTS_MODELS = [
-  "mimo-v2.5-tts",
-  "mimo-v2-tts",
-  XIAOMI_TTS_VOICE_DESIGN_MODEL,
-] as const;
+const XIAOMI_TTS_MODELS = ["mimo-v2.5-tts", "mimo-v2-tts", XIAOMI_TTS_VOICE_DESIGN_MODEL] as const;
 
 const XIAOMI_TTS_VOICES = [
   "mimo_default",
@@ -90,9 +86,12 @@ function normalizeXiaomiTtsProviderConfig(
     ),
     model:
       trimToUndefined(raw?.model) ??
+      trimToUndefined(raw?.modelId) ??
       trimToUndefined(process.env.XIAOMI_TTS_MODEL) ??
       DEFAULT_XIAOMI_TTS_MODEL,
     voice:
+      trimToUndefined(raw?.speakerVoice) ??
+      trimToUndefined(raw?.speakerVoiceId) ??
       trimToUndefined(raw?.voice) ??
       trimToUndefined(raw?.voiceId) ??
       trimToUndefined(process.env.XIAOMI_TTS_VOICE) ??
@@ -114,8 +113,13 @@ function readXiaomiTtsProviderConfig(config: SpeechProviderConfig): XiaomiTtsPro
         path: "messages.tts.providers.xiaomi.apiKey",
       }) ?? normalized.apiKey,
     baseUrl: normalizeXiaomiTtsBaseUrl(trimToUndefined(config.baseUrl) ?? normalized.baseUrl),
-    model: trimToUndefined(config.model) ?? normalized.model,
-    voice: trimToUndefined(config.voice) ?? trimToUndefined(config.voiceId) ?? normalized.voice,
+    model: trimToUndefined(config.model) ?? trimToUndefined(config.modelId) ?? normalized.model,
+    voice:
+      trimToUndefined(config.speakerVoice) ??
+      trimToUndefined(config.speakerVoiceId) ??
+      trimToUndefined(config.voice) ??
+      trimToUndefined(config.voiceId) ??
+      normalized.voice,
     format: normalizeXiaomiTtsFormat(config.format) ?? normalized.format,
     style: trimToUndefined(config.style) ?? normalized.style,
   };
@@ -128,8 +132,12 @@ function readXiaomiTtsOverrides(
     return {};
   }
   return {
-    model: trimToUndefined(overrides.model),
-    voice: trimToUndefined(overrides.voice) ?? trimToUndefined(overrides.voiceId),
+    model: trimToUndefined(overrides.model) ?? trimToUndefined(overrides.modelId),
+    voice:
+      trimToUndefined(overrides.speakerVoice) ??
+      trimToUndefined(overrides.speakerVoiceId) ??
+      trimToUndefined(overrides.voice) ??
+      trimToUndefined(overrides.voiceId),
     format: normalizeXiaomiTtsFormat(overrides.format),
     style: trimToUndefined(overrides.style),
   };
@@ -197,11 +205,10 @@ function resolveXiaomiVoiceDesignStyle(style: string | undefined): string {
   return trimToUndefined(style) ?? DEFAULT_XIAOMI_TTS_VOICE_DESIGN_STYLE;
 }
 
-function buildXiaomiTtsAudio(params: {
-  model: string;
-  voice: string;
+function buildXiaomiTtsAudio(params: { model: string; voice: string; format: XiaomiTtsFormat }): {
   format: XiaomiTtsFormat;
-}): { format: XiaomiTtsFormat; voice?: string } {
+  voice?: string;
+} {
   if (isXiaomiVoiceDesignModel(params.model)) {
     return { format: params.format };
   }