c570fe33ae
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.
54 lines
2.1 KiB
JavaScript
54 lines
2.1 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 xiaomiMimo from "./xiaomi-mimo.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,
|
|
"xiaomi-mimo": xiaomiMimo,
|
|
};
|
|
|
|
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 { PROVIDER_MODELS } = await import("open-sse/config/providerModels.js");
|
|
const ttsModels = (PROVIDER_MODELS[provider] || []).filter(m => (m.kind || m.type) === "tts");
|
|
const defaultModel = ttsModels[0]?.id || "";
|
|
const { modelId, voiceId } = parseModelVoice(model, defaultModel, "", ttsModels);
|
|
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 };
|