Merge remote-tracking branch 'origin/master' into gitea/feature/end

Resolved conflicts taking origin/master (v0.5.55) as canonical, with local
features re-applied:
- runtime log level (LOG_LEVEL env + dashboard Settings → Logging, applied
  immediately and persisted across restarts)
- free/noAuth provider enable/disable toggle via providerStrategies.enabled
- parallel model testing (Test All Models / Test Selected Keys)

open-sse/handlers/ttsProviders/genericFormats.js

@@ -51,6 +51,25 @@ async function huggingface({ baseUrl, apiKey, text, modelId }) {
   return responseToBase64(res, "wav");
 }
 
+// Fish Audio: model travels in an HTTP header, the voice is a reference_id, returns binary
+async function fishAudio({ baseUrl, apiKey, text, modelId, voiceId }) {
+  const res = await fetch(baseUrl, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      "Authorization": `Bearer ${apiKey}`,
+      "model": modelId || "s2.1-pro-free",
+    },
+    body: JSON.stringify({
+      text,
+      format: "mp3",
+      ...(voiceId ? { reference_id: voiceId } : {}),
+    }),
+  });
+  if (!res.ok) await throwUpstreamError(res);
+  return responseToBase64(res, "mp3");
+}
+
 // Inworld: Basic auth, JSON { audioContent }
 async function inworld({ baseUrl, apiKey, text, modelId, voiceId }) {
   const res = await fetch(baseUrl, {
@@ -166,4 +185,5 @@ export const FORMAT_HANDLERS = {
   tortoise,
   openai: openaiCompat,
   "minimax-tts": minimaxTts,
+  "fish-audio": fishAudio,
 };

open-sse/handlers/ttsProviders/index.js

@@ -6,6 +6,8 @@ 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 selfhostedTts from "./selfhostedTts.js";
 import { FORMAT_HANDLERS } from "./genericFormats.js";
 import { parseModelVoice } from "./_base.js";
 
@@ -18,6 +20,8 @@ const SPECIAL_ADAPTERS = {
   openai,
   openrouter,
   gemini,
+  "xiaomi-mimo": xiaomiMimo,
+  "selfhosted-tts": selfhostedTts,
 };
 
 export function getTtsAdapter(provider) {

open-sse/handlers/ttsProviders/selfhostedTts.js

@@ -0,0 +1,69 @@
+// Self-hosted OpenAI-compatible TTS — POST {baseUrl}/v1/audio/speech.
+//
+// A SPECIAL_ADAPTER rather than a genericFormats handler on purpose: the generic
+// dispatcher resolves baseUrl from the static registry entry
+// (`synthesizeViaConfig` reads `cfg.baseUrl`) and never looks at the connection,
+// which is exactly the limitation this provider exists to lift.
+import { Buffer } from "node:buffer";
+
+const DEFAULT_BASE_URL = "http://localhost:8880";
+const DEFAULT_MODEL = "kokoro";
+const DEFAULT_VOICE = "af_heart";
+
+export default {
+  async synthesize(text, model, credentials, responseFormat = "mp3") {
+    // Accept either providerSpecificData.baseUrl (how the custom embedding and
+    // STT providers carry it) or a bare credentials.baseUrl (how the OpenAI TTS
+    // adapter does), so a connection configured either way works.
+    const raw = credentials?.providerSpecificData?.baseUrl || credentials?.baseUrl || DEFAULT_BASE_URL;
+    // Tolerate a baseUrl given as the full endpoint or with a trailing /v1 —
+    // both are natural things to paste, and silently double-appending the path
+    // would 404 with nothing pointing at the cause.
+    const base = String(raw)
+      .replace(/\/+$/, "")
+      .replace(/\/v1\/audio\/speech$/, "")
+      .replace(/\/v1$/, "");
+
+    // The provider prefix is already stripped by getModelInfo, so `model` here is
+    // "kokoro" or "kokoro/af_heart" — NOT "selfhosted-tts/...".
+    //
+    // A bare value is the MODEL, not the voice. The OpenAI adapter reads a bare
+    // value as a voice, which is right for a service whose model is fixed
+    // ("tts-1") and whose voice varies — but wrong here, where the model is the
+    // variable part. Treating it as a voice sent voice="kokoro" upstream and
+    // Kokoro answered 400, so `selfhosted-tts/kokoro` — the obvious way to
+    // address this provider — was the one form that did not work (verified
+    // against a live Kokoro through 9router, 2026-08-03).
+    let ttsModel = DEFAULT_MODEL;
+    let voice = DEFAULT_VOICE;
+    if (model) {
+      const parts = String(model).split("/").filter(Boolean);
+      if (parts.length >= 2) {
+        ttsModel = parts[0];
+        voice = parts.slice(1).join("/");
+      } else if (parts.length === 1) {
+        ttsModel = parts[0];
+      }
+    }
+
+    const res = await fetch(`${base}/v1/audio/speech`, {
+      method: "POST",
+      headers: {
+        "Content-Type": "application/json",
+        ...(credentials?.apiKey ? { Authorization: `Bearer ${credentials.apiKey}` } : {}),
+      },
+      body: JSON.stringify({
+        model: ttsModel,
+        voice,
+        input: text,
+        response_format: responseFormat,
+      }),
+    });
+    if (!res.ok) {
+      const err = await res.json().catch(() => ({}));
+      throw new Error(err?.error?.message || `Self-hosted TTS failed: ${res.status}`);
+    }
+    const buf = await res.arrayBuffer();
+    return { base64: Buffer.from(buf).toString("base64"), format: responseFormat };
+  },
+};

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",
+  };
+}