Zonghao Yuan
e261f4a346
Reduce median scene-load latency from ~30-80s to ~17-25s by switching image generation to Runware FLUX.2 [klein] 9B KV and moving per-beat TTS synthesis off the scene response into a new lazy /api/beat-audio endpoint with hard timeout + abort support.
- feat(image): migrate to Runware FLUX.2 [klein] 9B KV — task-array API, $0.001/image, sub-second inference.
- feat(tts): split /api/scene into directScene + image + voicedesign-provisioning; lazily synth per beat via /api/beat-audio with 15s hard timeout + AbortSignal threaded to MiMo so timed-out calls don't keep burning sockets/quota; client fans out per-beat fetches on scene-id change with abort + identity-check finally to prevent cross-scene beat-id collisions.
- refactor(tts): slim BeatAudioRequest to { beat, voice } — ~800KB per-beat upload dropped to ~160KB by sending only the speaker's voice instead of the full session.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
37 lines
1.3 KiB
TypeScript
37 lines
1.3 KiB
TypeScript
import { requestBeatAudio } from "@yume/engine";
|
|
import type { BeatAudioRequest } from "@yume/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();
|
|
const result = await requestBeatAudio(config, body);
|
|
return NextResponse.json(result);
|
|
} 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 });
|
|
}
|
|
}
|