feat: add STT support, Gemini TTS, and expand usage tracking

- 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
This commit is contained in:
decolua
2026-05-05 10:32:59 +07:00
parent bfb7d42164
commit d4bc42e1f5
67 changed files with 2930 additions and 234 deletions
+1 -1
View File
@@ -49,7 +49,7 @@ async function probeMediaProvider(provider, apiKey) {
const kinds = p.serviceKinds || ["llm"];
const isMediaOnly = kinds.every((k) => MEDIA_KINDS.has(k));
if (!isMediaOnly) return null;
const cfg = p.ttsConfig || p.embeddingConfig || p.imageConfig || p.videoConfig || p.musicConfig;
const cfg = p.ttsConfig || p.sttConfig || p.embeddingConfig || p.imageConfig || p.videoConfig || p.musicConfig;
// No probe config → best-effort accept (validate at usage time)
if (!cfg) return true;
if (p.noAuth || cfg.authType === "none") return true;