mirror of
https://github.com/decolua/9router.git
synced 2026-05-08 12:01:28 +00:00
d4bc42e1f5
- Speech-to-Text: full pipeline with sttCore handler, /v1/audio/transcriptions endpoint, sttConfig for OpenAI, Gemini, Groq, Deepgram, AssemblyAI, HuggingFace, NVIDIA Parakeet; new 9router-stt skill - Gemini TTS: add gemini provider with 30 prebuilt voices and TTS_PROVIDER_CONFIG - Usage: implement GLM (intl/cn) and MiniMax (intl/cn) quota fetchers; refactor Gemini CLI usage to use retrieveUserQuota with per-model buckets - Disabled models: lowdb-backed disabledModelsDb + /api/models/disabled route - Header search: reusable Zustand store (headerSearchStore) wired into Header - CLI tools: add Claude Cowork tool card and cowork-settings API - Providers: introduce mediaPriority sorting in getProvidersByKind, add Kimi K2.6, reorder hermes, drop qwen STT kind - UI: expand media-providers/[kind]/[id] page (+314), enhance OAuthModal, ModelSelectModal, ProviderTopology, ProxyPools, ProviderLimits - Assets: refresh provider PNGs (alicode, byteplus, cloudflare-ai, nvidia, ollama, vertex, volcengine-ark) and add aws-polly, fal-ai, jina-ai, recraft, runwayml, stability-ai, topaz, black-forest-labs
51 lines
1.8 KiB
JavaScript
51 lines
1.8 KiB
JavaScript
// 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 };
|