feat(tts): add Xiaomi MiMo text-to-speech support

Adds mimo-v2.5-tts as a Media Provider TTS through the existing
OpenAI-compatible chat-completions endpoint. Voice is selected via the
top-level audio.voice field, and an optional style/language hint is
threaded through tts.js -> ttsCore.js -> the new adapter.

open-sse/config/ttsModels.js

@@ -33,6 +33,21 @@ const GEMINI_VOICES = [
   "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat",
 ].map((id) => ({ id, name: id, type: "tts" }));
 
+// Xiaomi MiMo preset voices (from https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5).
+// Voice id is passed via `audio.voice`; `mimo_default` = default (冰糖 on CN cluster, Mia elsewhere).
+// Voices are language-independent — the spoken language is a separate hint, not bound to the voice.
+const MIMO_VOICES = [
+  { id: "mimo_default", name: "mimo_default" },
+  { id: "冰糖",           name: "冰糖" },
+  { id: "茉莉",           name: "茉莉" },
+  { id: "苏打",           name: "苏打" },
+  { id: "白桦",           name: "白桦" },
+  { id: "Mia",           name: "Mia" },
+  { id: "Chloe",         name: "Chloe" },
+  { id: "Milo",          name: "Milo" },
+  { id: "Dean",          name: "Dean" },
+].map((v) => ({ type: "tts", ...v }));
+
 // ── TTS Config (config-driven, single source of truth) ─────────────────────
 export const TTS_MODELS_CONFIG = {
   openai: {
@@ -107,6 +122,14 @@ export const TTS_MODELS_CONFIG = {
     },
     allVoices: GEMINI_VOICES,
   },
+  "xiaomi-mimo": {
+    models: [
+      { id: "mimo-v2.5-tts", name: "MiMo V2.5 TTS", type: "tts" },
+    ],
+    voices: {
+      "mimo-v2.5-tts": MIMO_VOICES,
+    },
+  },
 };
 
 // ── Helper: get voices for a specific model ────────────────────────────────

open-sse/handlers/ttsCore.js

@@ -48,16 +48,16 @@ function createTtsResponse(base64Audio, format, responseFormat) {
  *
  * @returns {Promise<{success, response, status?, error?}>}
  */
-export async function handleTtsCore({ provider, model, input, credentials, responseFormat = "mp3", language }) {
+export async function handleTtsCore({ provider, model, input, credentials, responseFormat = "mp3", language, style }) {
   if (!input?.trim()) {
     return createErrorResult(HTTP_STATUS.BAD_REQUEST, "Missing required field: input");
   }
 
   try {
-    // Special-case adapters (google-tts, edge-tts, local-device, elevenlabs, openai, openrouter, gemini)
+    // Special-case adapters (google-tts, edge-tts, local-device, elevenlabs, openai, openrouter, gemini, xiaomi-mimo)
     const adapter = getTtsAdapter(provider);
     if (adapter) {
-      const result = await adapter.synthesize(input.trim(), model, credentials, responseFormat, { language });
+      const result = await adapter.synthesize(input.trim(), model, credentials, responseFormat, { language, style });
       // Adapter may return a full {success, response} (legacy) or {base64, format}
       if (result.success !== undefined) return result;
       return createTtsResponse(result.base64, result.format, responseFormat);

open-sse/handlers/ttsProviders/index.js

@@ -6,6 +6,7 @@ import elevenlabs, { fetchElevenLabsVoices } from "./elevenlabs.js";
 import openai from "./openai.js";
 import openrouter from "./openrouter.js";
 import gemini, { fetchGeminiVoices } from "./gemini.js";
+import xiaomiMimo from "./xiaomi-mimo.js";
 import { FORMAT_HANDLERS } from "./genericFormats.js";
 import { parseModelVoice } from "./_base.js";
 
@@ -18,6 +19,7 @@ const SPECIAL_ADAPTERS = {
   openai,
   openrouter,
   gemini,
+  "xiaomi-mimo": xiaomiMimo,
 };
 
 export function getTtsAdapter(provider) {

open-sse/handlers/ttsProviders/xiaomi-mimo.js

@@ -0,0 +1,65 @@
+// Xiaomi MiMo TTS — via OpenAI-compatible chat completions (non-streaming).
+// Docs: https://mimo.mi.com/docs/zh-CN/quick-start/usage-guide/audio/speech-synthesis-v2.5
+// Message contract: target text in `role: assistant` content, style/voice
+// instructions in `role: user` content. Voice is selected via the top-level
+// `audio.voice` field (NOT embedded in the model name).
+import { parseModelVoice } from "./_base.js";
+
+const DEFAULT_MODEL = "mimo-v2.5-tts";
+const DEFAULT_VOICE = "mimo_default";
+
+export default {
+  synthesize(text, model, credentials, responseFormat, { style, language } = {}) {
+    if (!credentials?.apiKey) throw new Error("xiaomi-mimo API key required");
+    return synthesizeMiMo(text, model, credentials.apiKey, style, language);
+  },
+};
+
+export async function synthesizeMiMo(text, model, apiKey, style, language) {
+  const { modelId, voiceId } = parseModelVoice(model, DEFAULT_MODEL, DEFAULT_VOICE, [DEFAULT_MODEL]);
+
+  // Language and style are soft instructions → prepend as a role:user message.
+  // MiMo auto-detects the spoken language of the text; the hint only nudges it
+  // (e.g. "Speak in English.") and is independent of the chosen voice.
+  const instructions = [];
+  if (language) instructions.push(`Speak in ${language}.`);
+  if (style) instructions.push(style);
+
+  const messages = [{ role: "assistant", content: text }];
+  if (instructions.length) messages.unshift({ role: "user", content: instructions.join(" ") });
+
+  const res = await fetch("https://api.xiaomimimo.com/v1/chat/completions", {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      "Authorization": `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify({
+      model: modelId,
+      stream: false,
+      messages,
+      audio: {
+        format: "wav",
+        voice: voiceId || DEFAULT_VOICE,
+      },
+    }),
+  });
+
+  const rawText = await res.text();
+  let data = {};
+  if (rawText) {
+    try { data = JSON.parse(rawText); } catch { data = {}; }
+  }
+
+  if (!res.ok) {
+    throw new Error(data?.error?.message || rawText || `MiMo TTS error (${res.status})`);
+  }
+
+  const audio = data?.choices?.[0]?.message?.audio?.data;
+  if (!audio) throw new Error(data?.error?.message || "MiMo TTS returned no audio");
+
+  return {
+    base64: audio,
+    format: data?.choices?.[0]?.message?.audio?.format || "wav",
+  };
+}

open-sse/providers/registry/xiaomi-mimo.js

@@ -15,10 +15,11 @@ export default {
     textIcon: "XM",
     website: "https://xiaomimimo.com",
     notice: {
-      apiKeyUrl: "https://xiaomimimo.com",
+      apiKeyUrl: "https://platform.xiaomimimo.com/console/api-keys",
     },
   },
   category: "apikey",
+  serviceKinds: ["llm", "tts"],
   transport: {
     baseUrl: "https://api.xiaomimimo.com/v1/chat/completions",
     validateUrl: "https://api.xiaomimimo.com/v1/models",
@@ -42,5 +43,12 @@ export default {
     { id: "mimo-v2.5", name: "MiMo V2.5" },
     { id: "mimo-v2-omni", name: "MiMo V2 Omni" },
     { id: "mimo-v2-flash", name: "MiMo V2 Flash" },
+    { id: "mimo-v2.5-tts", name: "MiMo V2.5 TTS", kind: "tts" },
   ],
+  ttsConfig: {
+    baseUrl: "https://api.xiaomimimo.com/v1/chat/completions",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "xiaomi-mimo-tts",
+  },
 };