@fudrouter/fsrouter 0.6.59 → 0.6.61

package/open-sse/handlers/ttsCore.js

@@ -1,74 +0,0 @@
-import { Buffer } from "node:buffer";
-import { createErrorResult } from "../utils/error.js";
-import { HTTP_STATUS } from "../config/runtimeConfig.js";
-import { getTtsAdapter, synthesizeViaConfig } from "./ttsProviders/index.js";
-
-// Re-export voice fetchers + voices APIs for backward compat with existing routes
-export {
-  VOICE_FETCHERS,
-  fetchEdgeTtsVoices,
-  fetchLocalDeviceVoices,
-  fetchElevenLabsVoices,
-} from "./ttsProviders/index.js";
-
-// ── Response Formatter (DRY) ───────────────────────────────────
-function createTtsResponse(base64Audio, format, responseFormat) {
-  const audioBuffer = Buffer.from(base64Audio, "base64");
-
-  // JSON format: return base64 encoded audio
-  if (responseFormat === "json") {
-    return {
-      success: true,
-      response: new Response(JSON.stringify({ audio: base64Audio, format }), {
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": "*",
-        },
-      }),
-    };
-  }
-
-  // Binary format (default): return raw audio
-  return {
-    success: true,
-    response: new Response(audioBuffer, {
-      headers: {
-        "Content-Type": `audio/${format}`,
-        "Content-Length": String(audioBuffer.length),
-        "Access-Control-Allow-Origin": "*",
-      },
-    }),
-  };
-}
-
-// ── Core handler ───────────────────────────────────────────────
-/**
- * Synthesize text to audio. Provider logic lives in `./ttsProviders/{id}.js`
- * or is dispatched generically via `ttsConfig.format`.
- *
- * @returns {Promise<{success, response, status?, error?}>}
- */
-export async function handleTtsCore({ provider, model, input, credentials, responseFormat = "mp3", language }) {
-  if (!input?.trim()) {
-    return createErrorResult(HTTP_STATUS.BAD_REQUEST, "Missing required field: input");
-  }
-
-  try {
-    // Special-case adapters (google-tts, edge-tts, local-device, elevenlabs, openai, openrouter, gemini)
-    const adapter = getTtsAdapter(provider);
-    if (adapter) {
-      const result = await adapter.synthesize(input.trim(), model, credentials, responseFormat, { language });
-      // Adapter may return a full {success, response} (legacy) or {base64, format}
-      if (result.success !== undefined) return result;
-      return createTtsResponse(result.base64, result.format, responseFormat);
-    }
-
-    // Generic config-driven (hyperbolic, deepgram, nvidia, huggingface, inworld, cartesia, playht, coqui, tortoise, qwen, ...)
-    const result = await synthesizeViaConfig(provider, input.trim(), model, credentials);
-    if (result) return createTtsResponse(result.base64, result.format, responseFormat);
-
-    return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Provider '${provider}' does not support TTS via this route.`);
-  } catch (err) {
-    return createErrorResult(HTTP_STATUS.BAD_GATEWAY, err.message || "TTS synthesis failed");
-  }
-}

package/open-sse/handlers/ttsProviders/_base.js

@@ -1,39 +0,0 @@
-// Shared TTS helpers
-import { Buffer } from "node:buffer";
-
-export const UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36";
-
-// Convert upstream Response (binary audio) to { base64, format }
-export async function responseToBase64(res, defaultFormat = "mp3") {
-  const buf = await res.arrayBuffer();
-  if (buf.byteLength < 100) throw new Error("Upstream returned empty audio");
-  const ctype = res.headers.get("content-type") || "";
-  let format = defaultFormat;
-  if (ctype.includes("wav")) format = "wav";
-  else if (ctype.includes("mpeg") || ctype.includes("mp3")) format = "mp3";
-  else if (ctype.includes("ogg")) format = "ogg";
-  return { base64: Buffer.from(buf).toString("base64"), format };
-}
-
-export async function throwUpstreamError(res) {
-  const text = await res.text().catch(() => "");
-  let msg = `Upstream error (${res.status})`;
-  try {
-    const parsed = JSON.parse(text);
-    msg = parsed?.error?.message || parsed?.message || parsed?.detail?.message || (typeof parsed?.detail === "string" ? parsed.detail : null) || text || msg;
-  } catch { msg = text || msg; }
-  throw new Error(msg);
-}
-
-// Parse `model` string as "modelId/voiceId" — match against known model list (longest prefix wins)
-export function parseModelVoice(model, defaultModel = "", defaultVoice = "", knownModels = []) {
-  if (!model) return { modelId: defaultModel, voiceId: defaultVoice };
-  const known = knownModels.map((m) => m.id || m).filter(Boolean).sort((a, b) => b.length - a.length);
-  for (const id of known) {
-    if (model === id) return { modelId: id, voiceId: defaultVoice };
-    if (model.startsWith(`${id}/`)) return { modelId: id, voiceId: model.slice(id.length + 1) };
-  }
-  const idx = model.lastIndexOf("/");
-  if (idx > 0) return { modelId: model.slice(0, idx), voiceId: model.slice(idx + 1) };
-  return { modelId: defaultModel || model, voiceId: defaultVoice || model };
-}

package/open-sse/handlers/ttsProviders/edgeTts.js

@@ -1,89 +0,0 @@
-// Microsoft Edge / Bing TTS (no auth) — via Bing translator endpoint
-import { Buffer } from "node:buffer";
-import { UA } from "./_base.js";
-
-const REFRESH_MS = 5 * 60 * 1000; // token TTL ~1h, refresh early
-const VOICES_TTL = 24 * 60 * 60 * 1000;
-
-const cache = { token: null, tokenTime: 0 };
-let _voicesCache = null;
-let _voicesCacheTime = 0;
-
-async function getToken() {
-  const now = Date.now();
-  if (cache.token && now - cache.tokenTime < REFRESH_MS) return cache.token;
-  const res = await fetch("https://www.bing.com/translator", {
-    headers: { "User-Agent": UA, "Accept-Language": "vi,en-US;q=0.9,en;q=0.8" },
-  });
-  if (!res.ok) throw new Error(`Bing translator fetch failed: ${res.status}`);
-  const rawCookies = res.headers.getSetCookie?.() || [];
-  const cookie = rawCookies.map((c) => c.split(";")[0]).join("; ");
-  const html = await res.text();
-  const match = html.match(/params_AbusePreventionHelper\s*=\s*\[([^,]+),([^,]+),/);
-  if (!match) throw new Error("Failed to parse Bing token");
-  cache.token = { key: match[1], token: match[2].replace(/"/g, ""), cookie };
-  cache.tokenTime = now;
-  return cache.token;
-}
-
-async function ttsRequest(text, voiceId, token) {
-  const parts = voiceId.split("-");
-  const xmlLang = parts.slice(0, 2).join("-");
-  const gender = voiceId.toLowerCase().includes("male") ? "Male" : "Female";
-  const ssml = `<speak version='1.0' xml:lang='${xmlLang}'><voice xml:lang='${xmlLang}' xml:gender='${gender}' name='${voiceId}'><prosody rate='0.00%'>${text}</prosody></voice></speak>`;
-  const body = new URLSearchParams();
-  body.append("ssml", ssml);
-  body.append("token", token.token);
-  body.append("key", token.key);
-  return fetch("https://www.bing.com/tfettts?isVertical=1&&IG=1&IID=translator.5023&SFX=1", {
-    method: "POST",
-    body: body.toString(),
-    headers: {
-      "Content-Type": "application/x-www-form-urlencoded",
-      "Accept": "*/*",
-      "Origin": "https://www.bing.com",
-      "Referer": "https://www.bing.com/translator",
-      "User-Agent": UA,
-      ...(token.cookie ? { "Cookie": token.cookie } : {}),
-    },
-  });
-}
-
-export async function fetchEdgeTtsVoices() {
-  const now = Date.now();
-  if (_voicesCache && now - _voicesCacheTime < VOICES_TTL) return _voicesCache;
-  const res = await fetch(
-    "https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=6A5AA1D4EAFF4E9FB37E23D68491D6F4",
-    { headers: { "User-Agent": UA } }
-  );
-  if (!res.ok) throw new Error(`Edge TTS voices fetch failed: ${res.status}`);
-  const voices = await res.json();
-  _voicesCache = voices;
-  _voicesCacheTime = now;
-  return voices;
-}
-
-export default {
-  noAuth: true,
-  async synthesize(text, model) {
-    const voiceId = model || "vi-VN-HoaiMyNeural";
-    let token = await getToken();
-    let res = await ttsRequest(text, voiceId, token);
-
-    // 429/403: invalidate cache and retry once
-    if (res.status === 429 || res.status === 403) {
-      cache.token = null;
-      cache.tokenTime = 0;
-      token = await getToken();
-      res = await ttsRequest(text, voiceId, token);
-    }
-
-    if (!res.ok) {
-      const body = await res.text().catch(() => "");
-      throw new Error(`Bing TTS failed: ${res.status}${body ? " - " + body : ""}`);
-    }
-    const buf = await res.arrayBuffer();
-    if (buf.byteLength < 1024) throw new Error("Bing TTS returned empty audio");
-    return { base64: Buffer.from(buf).toString("base64"), format: "mp3" };
-  },
-};

package/open-sse/handlers/ttsProviders/elevenlabs.js

@@ -1,48 +0,0 @@
-// ElevenLabs TTS — voice id with optional model_id prefix
-import { Buffer } from "node:buffer";
-
-const VOICES_TTL = 24 * 60 * 60 * 1000;
-const _voicesCache = new Map(); // by API key
-
-export async function fetchElevenLabsVoices(apiKey) {
-  if (!apiKey) throw new Error("ElevenLabs API key required");
-  const now = Date.now();
-  const cached = _voicesCache.get(apiKey);
-  if (cached && now - cached.time < VOICES_TTL) return cached.voices;
-
-  const res = await fetch("https://api.elevenlabs.io/v1/voices", {
-    headers: { "xi-api-key": apiKey, "Content-Type": "application/json" },
-  });
-  if (!res.ok) throw new Error(`ElevenLabs voices fetch failed: ${res.status}`);
-  const data = await res.json();
-  // Normalize: derive lang from labels for grouping
-  const voices = (data.voices || []).map((v) => ({ ...v, lang: v.labels?.language || "en" }));
-  _voicesCache.set(apiKey, { voices, time: now });
-  return voices;
-}
-
-export default {
-  async synthesize(text, model, credentials) {
-    if (!credentials?.apiKey) throw new Error("ElevenLabs API key required");
-    let modelId = "eleven_flash_v2_5";
-    let voiceId = model;
-    if (model && model.includes("/")) [modelId, voiceId] = model.split("/");
-
-    const res = await fetch(`https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`, {
-      method: "POST",
-      headers: { "xi-api-key": credentials.apiKey, "Content-Type": "application/json" },
-      body: JSON.stringify({
-        text,
-        model_id: modelId,
-        voice_settings: { stability: 0.5, similarity_boost: 0.75 },
-      }),
-    });
-    if (!res.ok) {
-      const err = await res.json().catch(() => ({}));
-      throw new Error(err?.detail?.message || `ElevenLabs TTS failed: ${res.status}`);
-    }
-    const buf = await res.arrayBuffer();
-    if (buf.byteLength < 1024) throw new Error("ElevenLabs TTS returned empty audio");
-    return { base64: Buffer.from(buf).toString("base64"), format: "mp3" };
-  },
-};

package/open-sse/handlers/ttsProviders/gemini.js

@@ -1,117 +0,0 @@
-// Gemini TTS — generateContent with AUDIO modality returns PCM L16, wrap as WAV
-import { Buffer } from "node:buffer";
-
-const DEFAULT_MODEL = "gemini-2.5-flash-preview-tts";
-const DEFAULT_VOICE = "Kore";
-const KNOWN_MODELS = ["gemini-2.5-flash-preview-tts", "gemini-2.5-pro-preview-tts"];
-
-// Parse "model/voice" — if input doesn't match a known TTS model, treat it as voice with default model
-function parseGeminiModelVoice(input) {
-  if (!input) return { modelId: DEFAULT_MODEL, voiceId: DEFAULT_VOICE };
-  for (const id of KNOWN_MODELS) {
-    if (input === id) return { modelId: id, voiceId: DEFAULT_VOICE };
-    if (input.startsWith(`${id}/`)) return { modelId: id, voiceId: input.slice(id.length + 1) };
-  }
-  return { modelId: DEFAULT_MODEL, voiceId: input };
-}
-// Gemini returns PCM 16-bit signed mono @ 24kHz
-const SAMPLE_RATE = 24000;
-const CHANNELS = 1;
-const BITS_PER_SAMPLE = 16;
-
-// Build WAV header for raw PCM payload
-function pcmToWav(pcmBuffer) {
-  const dataSize = pcmBuffer.length;
-  const byteRate = SAMPLE_RATE * CHANNELS * BITS_PER_SAMPLE / 8;
-  const blockAlign = CHANNELS * BITS_PER_SAMPLE / 8;
-  const header = Buffer.alloc(44);
-  header.write("RIFF", 0);
-  header.writeUInt32LE(36 + dataSize, 4);
-  header.write("WAVE", 8);
-  header.write("fmt ", 12);
-  header.writeUInt32LE(16, 16);
-  header.writeUInt16LE(1, 20);
-  header.writeUInt16LE(CHANNELS, 22);
-  header.writeUInt32LE(SAMPLE_RATE, 24);
-  header.writeUInt32LE(byteRate, 28);
-  header.writeUInt16LE(blockAlign, 32);
-  header.writeUInt16LE(BITS_PER_SAMPLE, 34);
-  header.write("data", 36);
-  header.writeUInt32LE(dataSize, 40);
-  return Buffer.concat([header, pcmBuffer]);
-}
-
-// Build TTS prompt: add "Say [in {language}]:" prefix to force TTS mode
-function buildPrompt(text, language) {
-  if (/:\s/.test(text)) return text; // user already provided style instruction
-  return language ? `Say in ${language}: ${text}` : `Say: ${text}`;
-}
-
-export default {
-  async synthesize(text, model, credentials, _responseFormat, opts = {}) {
-    if (!credentials?.apiKey) throw new Error("No Gemini API key configured");
-    const { modelId, voiceId } = parseGeminiModelVoice(model);
-    const url = `https://generativelanguage.googleapis.com/v1beta/models/${modelId}:generateContent?key=${credentials.apiKey}`;
-    const res = await fetch(url, {
-      method: "POST",
-      headers: { "Content-Type": "application/json" },
-      body: JSON.stringify({
-        contents: [{ parts: [{ text: buildPrompt(text, opts.language) }] }],
-        generationConfig: {
-          responseModalities: ["AUDIO"],
-          speechConfig: { voiceConfig: { prebuiltVoiceConfig: { voiceName: voiceId } } },
-        },
-      }),
-    });
-    if (!res.ok) {
-      const err = await res.json().catch(() => ({}));
-      throw new Error(err?.error?.message || `Gemini TTS failed: ${res.status}`);
-    }
-    const data = await res.json();
-    const b64 = data?.candidates?.[0]?.content?.parts?.find((p) => p.inlineData?.data)?.inlineData?.data;
-    if (!b64) {
-      const reason = data?.candidates?.[0]?.finishReason || data?.promptFeedback?.blockReason || "unknown";
-      throw new Error(`Gemini TTS returned no audio (finishReason: ${reason}, voice: ${voiceId}, model: ${modelId})`);
-    }
-    const wav = pcmToWav(Buffer.from(b64, "base64"));
-    return { base64: wav.toString("base64"), format: "wav" };
-  },
-};
-
-// Voice fetcher — return prebuilt voices (Gemini has no list API)
-const PREBUILT_VOICES = [
-  { id: "Zephyr", lang: "en", gender: "Female" },
-  { id: "Puck", lang: "en", gender: "Male" },
-  { id: "Charon", lang: "en", gender: "Male" },
-  { id: "Kore", lang: "en", gender: "Female" },
-  { id: "Fenrir", lang: "en", gender: "Male" },
-  { id: "Leda", lang: "en", gender: "Female" },
-  { id: "Orus", lang: "en", gender: "Male" },
-  { id: "Aoede", lang: "en", gender: "Female" },
-  { id: "Callirrhoe", lang: "en", gender: "Female" },
-  { id: "Autonoe", lang: "en", gender: "Female" },
-  { id: "Enceladus", lang: "en", gender: "Male" },
-  { id: "Iapetus", lang: "en", gender: "Male" },
-  { id: "Umbriel", lang: "en", gender: "Male" },
-  { id: "Algieba", lang: "en", gender: "Male" },
-  { id: "Despina", lang: "en", gender: "Female" },
-  { id: "Erinome", lang: "en", gender: "Female" },
-  { id: "Algenib", lang: "en", gender: "Male" },
-  { id: "Rasalgethi", lang: "en", gender: "Male" },
-  { id: "Laomedeia", lang: "en", gender: "Female" },
-  { id: "Achernar", lang: "en", gender: "Female" },
-  { id: "Alnilam", lang: "en", gender: "Male" },
-  { id: "Schedar", lang: "en", gender: "Male" },
-  { id: "Gacrux", lang: "en", gender: "Female" },
-  { id: "Pulcherrima", lang: "en", gender: "Female" },
-  { id: "Achird", lang: "en", gender: "Male" },
-  { id: "Zubenelgenubi", lang: "en", gender: "Male" },
-  { id: "Vindemiatrix", lang: "en", gender: "Female" },
-  { id: "Sadachbia", lang: "en", gender: "Male" },
-  { id: "Sadaltager", lang: "en", gender: "Male" },
-  { id: "Sulafat", lang: "en", gender: "Female" },
-];
-
-export async function fetchGeminiVoices() {
-  return PREBUILT_VOICES.map((v) => ({ voice_id: v.id, name: v.id, labels: { language: v.lang, gender: v.gender } }));
-}

package/open-sse/handlers/ttsProviders/genericFormats.js

@@ -1,169 +0,0 @@
-// Generic config-driven TTS handlers — dispatched by ttsConfig.format.
-// Each handler accepts { baseUrl, apiKey, text, modelId, voiceId } and returns { base64, format }.
-import { responseToBase64, throwUpstreamError } from "./_base.js";
-import minimaxTts from "./minimax.js";
-
-// Hyperbolic: POST { text } → { audio: base64 }
-async function hyperbolic({ baseUrl, apiKey, text }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: { "Content-Type": "application/json", "Authorization": `Bearer ${apiKey}` },
-    body: JSON.stringify({ text }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  const data = await res.json();
-  return { base64: data.audio, format: "mp3" };
-}
-
-// Deepgram: model via query, Token auth, returns binary
-async function deepgram({ baseUrl, apiKey, text, modelId }) {
-  const url = new URL(baseUrl);
-  url.searchParams.set("model", modelId || "aura-asteria-en");
-  const res = await fetch(url.toString(), {
-    method: "POST",
-    headers: { "Content-Type": "application/json", "Authorization": `Token ${apiKey}` },
-    body: JSON.stringify({ text }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "mp3");
-}
-
-// Nvidia NIM: POST { input: { text }, voice, model } → binary
-async function nvidia({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: { "Content-Type": "application/json", "Authorization": `Bearer ${apiKey}` },
-    body: JSON.stringify({ input: { text }, voice: voiceId || "default", model: modelId }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "wav");
-}
-
-// HuggingFace: POST {baseUrl}/{modelId} { inputs: text } → binary
-async function huggingface({ baseUrl, apiKey, text, modelId }) {
-  if (!modelId || modelId.includes("..")) throw new Error("Invalid HuggingFace model ID");
-  const res = await fetch(`${baseUrl}/${modelId}`, {
-    method: "POST",
-    headers: { "Content-Type": "application/json", "Authorization": `Bearer ${apiKey}` },
-    body: JSON.stringify({ inputs: text }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "wav");
-}
-
-// Inworld: Basic auth, JSON { audioContent }
-async function inworld({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: { "Content-Type": "application/json", "Authorization": `Basic ${apiKey}` },
-    body: JSON.stringify({
-      text,
-      voiceId: voiceId || "Alex",
-      modelId: modelId || "inworld-tts-1.5-mini",
-      audioConfig: { audioEncoding: "MP3" },
-    }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  const data = await res.json();
-  if (!data.audioContent) throw new Error("Inworld TTS returned no audio");
-  return { base64: data.audioContent, format: "mp3" };
-}
-
-// Cartesia: X-API-Key header
-async function cartesia({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      "X-API-Key": apiKey,
-      "Cartesia-Version": "2024-06-10",
-    },
-    body: JSON.stringify({
-      model_id: modelId || "sonic-2",
-      transcript: text,
-      ...(voiceId ? { voice: { mode: "id", id: voiceId } } : {}),
-      output_format: { container: "mp3", bit_rate: 128000, sample_rate: 44100 },
-    }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "mp3");
-}
-
-// PlayHT: token format "userId:apiKey", voice = s3 URL
-async function playht({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const [userId, key] = (apiKey || ":").split(":");
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: {
-      "Content-Type": "application/json",
-      "Accept": "audio/mpeg",
-      "X-USER-ID": userId || "",
-      "Authorization": `Bearer ${key || apiKey}`,
-    },
-    body: JSON.stringify({
-      text,
-      voice: voiceId || "s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
-      voice_engine: modelId || "PlayDialog",
-      output_format: "mp3",
-      speed: 1,
-    }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "mp3");
-}
-
-// Coqui (local, noAuth): POST { text, speaker_id } → WAV
-async function coqui({ baseUrl, text, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: { "Content-Type": "application/json" },
-    body: JSON.stringify({ text, ...(voiceId ? { speaker_id: voiceId } : {}) }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "wav");
-}
-
-// Tortoise (local, noAuth)
-async function tortoise({ baseUrl, text, voiceId }) {
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers: { "Content-Type": "application/json" },
-    body: JSON.stringify({ text, voice: voiceId || "random" }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "wav");
-}
-
-// OpenAI-compatible upstream (qwen3-tts, etc.)
-async function openaiCompat({ baseUrl, apiKey, text, modelId, voiceId }) {
-  const headers = { "Content-Type": "application/json" };
-  if (apiKey) headers["Authorization"] = `Bearer ${apiKey}`;
-  const res = await fetch(baseUrl, {
-    method: "POST",
-    headers,
-    body: JSON.stringify({
-      model: modelId,
-      input: text,
-      voice: voiceId || "alloy",
-      response_format: "mp3",
-      speed: 1.0,
-    }),
-  });
-  if (!res.ok) await throwUpstreamError(res);
-  return responseToBase64(res, "mp3");
-}
-
-// format → handler dispatcher
-export const FORMAT_HANDLERS = {
-  hyperbolic,
-  deepgram,
-  "nvidia-tts": nvidia,
-  "huggingface-tts": huggingface,
-  inworld,
-  cartesia,
-  playht,
-  coqui,
-  tortoise,
-  openai: openaiCompat,
-  "minimax-tts": minimaxTts,
-};

package/open-sse/handlers/ttsProviders/googleTts.js

@@ -1,54 +0,0 @@
-// Google Translate TTS (no auth) — scrape token + batchexecute RPC
-import { UA } from "./_base.js";
-
-const REFRESH_MS = 11 * 60 * 1000;
-const cache = { token: null, tokenTime: 0 };
-let _idx = 0;
-
-async function getToken() {
-  const now = Date.now();
-  if (cache.token && now - cache.tokenTime < REFRESH_MS) return cache.token;
-  const res = await fetch("https://translate.google.com/", { headers: { "User-Agent": UA } });
-  if (!res.ok) throw new Error(`Google translate fetch failed: ${res.status}`);
-  const html = await res.text();
-  const fSid = html.match(/"FdrFJe":"(.*?)"/)?.[1];
-  const bl = html.match(/"cfb2h":"(.*?)"/)?.[1];
-  if (!fSid || !bl) throw new Error("Failed to parse Google token");
-  cache.token = { "f.sid": fSid, bl };
-  cache.tokenTime = now;
-  return cache.token;
-}
-
-export default {
-  noAuth: true,
-  async synthesize(text, model) {
-    const lang = model || "en";
-    const token = await getToken();
-    const cleanText = text.replace(/[@^*()\\/\-_+=><"'\u201c\u201d\u3010\u3011]/g, " ").replaceAll(", ", ". ");
-    const rpcId = "jQ1olc";
-    const reqId = (++_idx * 100000) + Math.floor(1000 + Math.random() * 9000);
-    const query = new URLSearchParams({
-      rpcids: rpcId,
-      "f.sid": token["f.sid"],
-      bl: token.bl,
-      hl: lang,
-      "soc-app": 1, "soc-platform": 1, "soc-device": 1,
-      _reqid: reqId,
-      rt: "c",
-    });
-    const payload = [cleanText, lang, null, "undefined", [0]];
-    const body = new URLSearchParams();
-    body.append("f.req", JSON.stringify([[[rpcId, JSON.stringify(payload), null, "generic"]]]));
-    const res = await fetch(`https://translate.google.com/_/TranslateWebserverUi/data/batchexecute?${query}`, {
-      method: "POST",
-      headers: { "Content-Type": "application/x-www-form-urlencoded", "Referer": "https://translate.google.com/" },
-      body: body.toString(),
-    });
-    if (!res.ok) throw new Error(`Google TTS failed: ${res.status}`);
-    const data = await res.text();
-    const split = JSON.parse(data.split("\n")[3]);
-    const base64 = JSON.parse(split[0][2])[0];
-    if (!base64 || base64.length < 100) throw new Error("Google TTS returned empty audio");
-    return { base64, format: "mp3" };
-  },
-};

package/open-sse/handlers/ttsProviders/index.js

@@ -1,50 +0,0 @@
-// TTS provider registry
-import googleTts from "./googleTts.js";
-import edgeTts, { fetchEdgeTtsVoices } from "./edgeTts.js";
-import localDevice, { fetchLocalDeviceVoices } from "./localDevice.js";
-import elevenlabs, { fetchElevenLabsVoices } from "./elevenlabs.js";
-import openai from "./openai.js";
-import openrouter from "./openrouter.js";
-import gemini, { fetchGeminiVoices } from "./gemini.js";
-import { FORMAT_HANDLERS } from "./genericFormats.js";
-import { parseModelVoice } from "./_base.js";
-
-// Special providers with custom synthesize() logic
-const SPECIAL_ADAPTERS = {
-  "google-tts": googleTts,
-  "edge-tts": edgeTts,
-  "local-device": localDevice,
-  elevenlabs,
-  openai,
-  openrouter,
-  gemini,
-};
-
-export function getTtsAdapter(provider) {
-  return SPECIAL_ADAPTERS[provider] || null;
-}
-
-// Generic config-driven dispatcher (uses ttsConfig.format)
-export async function synthesizeViaConfig(provider, text, model, credentials) {
-  const { AI_PROVIDERS } = await import("@/shared/constants/providers");
-  const cfg = AI_PROVIDERS[provider]?.ttsConfig;
-  if (!cfg) return null;
-  const handler = FORMAT_HANDLERS[cfg.format];
-  if (!handler) return null;
-  const apiKey = credentials?.apiKey;
-  if (cfg.authType !== "none" && !apiKey) throw new Error(`${provider} API key required`);
-  const defaultModel = cfg.models?.[0]?.id || "";
-  const { modelId, voiceId } = parseModelVoice(model, defaultModel, "", cfg.models || []);
-  return handler({ baseUrl: cfg.baseUrl, apiKey, text, modelId, voiceId });
-}
-
-// Voice fetchers (used by /api/media-providers/tts/voices route)
-export const VOICE_FETCHERS = {
-  "edge-tts": fetchEdgeTtsVoices,
-  "local-device": fetchLocalDeviceVoices,
-  elevenlabs: fetchElevenLabsVoices,
-  gemini: fetchGeminiVoices,
-};
-
-// Re-export for backward compat
-export { fetchEdgeTtsVoices, fetchLocalDeviceVoices, fetchElevenLabsVoices, fetchGeminiVoices };