yuanzonghao
e88e988de3
Three transport-only optimizations that cut per-session Vercel FOT by ~50-60%: P0 — Server strips voice.referenceAudioBase64 from already-known characters in /api/scene and /api/insert-beat responses (defense-in-depth). P1 — Client strips all voice data from session before sending to /api/scene, /api/vision, and /api/insert-beat. Voices are retained locally and re-merged from responses via mergeCharactersPreserveVoice(). The engine only needs character names + visualDescriptions for scene generation. P3 — /api/beat-audio returns binary audio (Response with Content-Type) instead of JSON-wrapped base64, saving ~33% encoding overhead. Client converts to blob URLs; PlayCanvas accepts a single audioSrc prop. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
41 lines
1.5 KiB
TypeScript
41 lines
1.5 KiB
TypeScript
import { requestBeatAudio } from "@infiplot/engine";
|
|
import type { BeatAudioRequest } from "@infiplot/types";
|
|
import { NextResponse } from "next/server";
|
|
import { loadEngineConfig } from "@/lib/config";
|
|
|
|
export const runtime = "nodejs";
|
|
// The synth itself has a 15s per-call ceiling in the engine. 30s here just
|
|
// covers JSON parsing + outbound network buffer.
|
|
export const maxDuration = 30;
|
|
|
|
export async function POST(req: Request) {
|
|
let body: BeatAudioRequest;
|
|
try {
|
|
body = (await req.json()) as BeatAudioRequest;
|
|
} catch {
|
|
return NextResponse.json({ error: "Invalid JSON" }, { status: 400 });
|
|
}
|
|
|
|
if (!body.beat?.id || !body.beat?.line || !body.voice?.referenceAudioBase64) {
|
|
return NextResponse.json(
|
|
{ error: "beat.id, beat.line and voice.referenceAudioBase64 are required" },
|
|
{ status: 400 },
|
|
);
|
|
}
|
|
|
|
try {
|
|
const config = loadEngineConfig(req.headers);
|
|
const result = await requestBeatAudio(config, body);
|
|
if (!result.audio) return new Response(null, { status: 204 });
|
|
const binary = Buffer.from(result.audio.base64, "base64");
|
|
return new Response(binary, {
|
|
headers: { "Content-Type": result.audio.mime },
|
|
});
|
|
} catch (err) {
|
|
// Engine already swallows synth errors and returns audio:null. Anything
|
|
// that reaches here is config-level — surface so the client can log it.
|
|
const message = err instanceof Error ? err.message : "Unknown error";
|
|
return NextResponse.json({ error: message }, { status: 500 });
|
|
}
|
|
}
|