decolua
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
123 lines
3.2 KiB
JavaScript
123 lines
3.2 KiB
JavaScript
/**
|
|
* TTS Provider Configuration
|
|
* Centralized config for TTS provider UI behavior
|
|
*/
|
|
export const TTS_PROVIDER_CONFIG = {
|
|
"google-tts": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: false,
|
|
hasBrowseButton: true,
|
|
voiceSource: "hardcoded", // languages built from providerModels at runtime
|
|
},
|
|
"openai": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
voiceSource: "hardcoded",
|
|
modelKey: "openai-tts-models",
|
|
voiceKey: "openai-tts-voices",
|
|
voicesPerModel: true,
|
|
},
|
|
"openrouter": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
voiceSource: "hardcoded",
|
|
modelKey: "openrouter-tts-models",
|
|
voiceKey: "openrouter-tts-voices",
|
|
voicesPerModel: true,
|
|
},
|
|
"elevenlabs": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: true,
|
|
hasBrowseButton: true,
|
|
hasVoiceIdInput: true, // allow manual voice id entry
|
|
voiceSource: "api-language", // grouped by language from backend
|
|
modelKey: "elevenlabs-tts-models",
|
|
apiEndpoint: "/api/media-providers/tts/elevenlabs/voices",
|
|
},
|
|
"edge-tts": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: false,
|
|
hasBrowseButton: true,
|
|
voiceSource: "api-language", // from API with language picker
|
|
},
|
|
"local-device": {
|
|
hasLanguageDropdown: false,
|
|
hasModelSelector: false,
|
|
hasBrowseButton: true,
|
|
voiceSource: "api-language", // from API with language picker
|
|
},
|
|
// ── Config-driven providers (load models from providers.js → ttsConfig.models) ──
|
|
"nvidia": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"hyperbolic": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
voiceSource: "config",
|
|
},
|
|
"deepgram": {
|
|
hasModelSelector: false,
|
|
hasBrowseButton: true,
|
|
voiceSource: "api-language",
|
|
apiEndpoint: "/api/media-providers/tts/deepgram/voices",
|
|
},
|
|
"huggingface": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
voiceSource: "config",
|
|
},
|
|
"cartesia": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"playht": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"coqui": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"tortoise": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"inworld": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: true,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "api-language",
|
|
modelKey: "inworld-tts-models",
|
|
apiEndpoint: "/api/media-providers/tts/inworld/voices",
|
|
},
|
|
"qwen": {
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
hasVoiceIdInput: true,
|
|
voiceSource: "config",
|
|
},
|
|
"gemini": {
|
|
hasLanguageDropdown: false,
|
|
hasLanguageHint: true, // sends body.language to guide TTS pronunciation
|
|
hasModelSelector: true,
|
|
hasBrowseButton: false,
|
|
voiceSource: "hardcoded",
|
|
modelKey: "gemini-tts-models",
|
|
voiceKey: "gemini-tts-voices",
|
|
voicesPerModel: true,
|
|
},
|
|
};
|