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
19 lines
529 B
JavaScript
19 lines
529 B
JavaScript
import { handleStt } from "@/sse/handlers/stt.js";
|
|
|
|
// Allow large audio uploads — 5min for processing large files
|
|
export const maxDuration = 300;
|
|
|
|
export async function OPTIONS() {
|
|
return new Response(null, {
|
|
headers: {
|
|
"Access-Control-Allow-Origin": "*",
|
|
"Access-Control-Allow-Methods": "POST, OPTIONS",
|
|
"Access-Control-Allow-Headers": "*",
|
|
},
|
|
});
|
|
}
|
|
|
|
/** POST /v1/audio/transcriptions - OpenAI Whisper compatible STT */
|
|
export async function POST(request) {
|
|
return await handleStt(request);
|
|
}
|