yuanzonghao
b0b2e922d3
Public users share one server TTS key, so Xiaomi's per-key RPM/TPM limits
cause silent playback under concurrency. This adds an OPTIONAL path: a user
can store their own Xiaomi MiMo key in the browser and synthesize voice
client-side against Xiaomi's CORS-open endpoints. The key lives only in
localStorage and is never sent to or logged by our server; the shared server
key still serves everyone who does not opt in.
- components/TtsKeyModal.tsx: shared key modal (key-family + region picker),
reused by both the home and play pages
- app/play/page.tsx: silence nudge moved beside the mute toggle; modal opens
in place instead of redirecting to the home page
- app/page.tsx: home page consumes the shared modal + readStoredTtsConfig
- lib/clientTtsConfig.ts, lib/ttsPresets.ts: browser config + region presets
- app/api/{start,scene,insert-beat}: thread per-request voice; lib/types update
- docs/xiaomi-tts-key.md + README note
Verified with tsc --noEmit (exit 0).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
36 lines
1.3 KiB
TypeScript
36 lines
1.3 KiB
TypeScript
import { requestScene } from "@infiplot/engine";
|
||
import type { SceneRequest } from "@infiplot/types";
|
||
import { NextResponse } from "next/server";
|
||
import { loadEngineConfig } from "@/lib/config";
|
||
|
||
export const runtime = "nodejs";
|
||
// Capped at 60 for Vercel Hobby (300 allowed on Pro). The scene pipeline is
|
||
// Writer + CharDesigner×N + Cinematographer + Painter — happy path 9–12s; the
|
||
// tail (cold provider, multiple new characters) can push 30–45s, so 60 is a
|
||
// reasonable headroom on Hobby.
|
||
export const maxDuration = 60;
|
||
|
||
export async function POST(req: Request) {
|
||
let body: SceneRequest;
|
||
try {
|
||
body = (await req.json()) as SceneRequest;
|
||
} catch {
|
||
return NextResponse.json({ error: "Invalid JSON" }, { status: 400 });
|
||
}
|
||
|
||
if (!body.session) {
|
||
return NextResponse.json({ error: "session is required" }, { status: 400 });
|
||
}
|
||
|
||
try {
|
||
const base = loadEngineConfig(req.headers);
|
||
// See StartRequest.clientTts — BYO clients synth in-browser, so drop server TTS.
|
||
const config = body.clientTts ? { ...base, tts: undefined } : base;
|
||
const result = await requestScene(config, body);
|
||
return NextResponse.json(result);
|
||
} catch (err) {
|
||
const message = err instanceof Error ? err.message : "Unknown error";
|
||
return NextResponse.json({ error: message }, { status: 500 });
|
||
}
|
||
}
|