feat: Runware FLUX.2 image + lazy per-beat TTS (#5)

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)

packages/tts-client/src/xiaomi.ts

@@ -77,6 +77,7 @@ export async function xiaomiSynthesize(
   voice: CharacterVoice,
   text: string,
   delivery?: string,
+  signal?: AbortSignal,
 ): Promise<{ audioBase64: string; mimeType: string }> {
   const url = joinUrl(cfg.baseUrl, "/chat/completions");
 
@@ -99,6 +100,7 @@ export async function xiaomiSynthesize(
     method: "POST",
     headers: buildHeaders(cfg),
     body: JSON.stringify(body),
+    signal,
   });
 
   if (!res.ok) {