fix(web): reduce FOT by stripping redundant voice data from transport

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>

app/api/beat-audio/route.ts

@@ -26,7 +26,11 @@ export async function POST(req: Request) {
   try {
     const config = loadEngineConfig(req.headers);
     const result = await requestBeatAudio(config, body);
-    return NextResponse.json(result);
+    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.

app/api/insert-beat/route.ts

@@ -26,7 +26,10 @@ export async function POST(req: Request) {
     // See StartRequest.clientTts — BYO clients synth in-browser, so drop server TTS.
     const config = body.clientTts === true ? { ...base, tts: undefined } : base;
     const result = await requestInsertBeat(config, body);
-    return NextResponse.json(result);
+    return NextResponse.json({
+      ...result,
+      characters: result.characters.map((c) => ({ ...c, voice: undefined })),
+    });
   } catch (err) {
     const message = err instanceof Error ? err.message : "Unknown error";
     return NextResponse.json({ error: message }, { status: 500 });

app/api/scene/route.ts

@@ -1,8 +1,17 @@
 import { requestScene } from "@infiplot/engine";
-import type { SceneRequest } from "@infiplot/types";
+import type { Character, SceneRequest } from "@infiplot/types";
 import { NextResponse } from "next/server";
 import { loadEngineConfig } from "@/lib/config";
 
+function stripKnownVoices(
+  characters: Character[],
+  knownNames: Set<string>,
+): Character[] {
+  return characters.map((c) =>
+    knownNames.has(c.name) ? { ...c, voice: undefined } : c,
+  );
+}
+
 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
@@ -27,7 +36,13 @@ export async function POST(req: Request) {
     // See StartRequest.clientTts — BYO clients synth in-browser, so drop server TTS.
     const config = body.clientTts === true ? { ...base, tts: undefined } : base;
     const result = await requestScene(config, body);
-    return NextResponse.json(result);
+    const knownNames = new Set(
+      (body.session.characters ?? []).map((c) => c.name),
+    );
+    return NextResponse.json({
+      ...result,
+      characters: stripKnownVoices(result.characters, knownNames),
+    });
   } catch (err) {
     const message = err instanceof Error ? err.message : "Unknown error";
     return NextResponse.json({ error: message }, { status: 500 });