Merge pull request #57 from zonghaoyuan/feat/tts-stepfun-provider

feat(tts): add StepFun preset-voice provider, route by URL + voice tag

app/api/beat-audio/route.ts

@@ -13,9 +13,18 @@ export async function POST(req: Request) {
     return NextResponse.json({ error: "Invalid JSON" }, { status: 400 });
   }
 
-  if (!body.beat?.id || !body.beat?.line || !body.voice?.referenceAudioBase64) {
+  // Accept either provider's voice shape — xiaomi carries referenceAudioBase64,
+  // stepfun carries voiceId. We only check the discriminator + the line text;
+  // shape-specific validation lives in each provider's synth function.
+  const VALID_TTS_PROVIDERS = ["xiaomi", "stepfun"];
+  if (
+    !body.beat?.id ||
+    !body.beat?.line ||
+    !body.voice?.provider ||
+    !VALID_TTS_PROVIDERS.includes(body.voice.provider)
+  ) {
     return NextResponse.json(
-      { error: "beat.id, beat.line and voice.referenceAudioBase64 are required" },
+      { error: "beat.id, beat.line and voice.provider (xiaomi|stepfun) are required" },
       { status: 400 },
     );
   }

app/play/page.tsx

@@ -525,7 +525,7 @@ async function resolveByoVoice(
     return ready;
   }
   if (!speaker.voiceDescription) return null;
-  const p = provisionVoice(cfg, speaker.voiceDescription);
+  const p = provisionVoice(cfg, speaker.voiceDescription, speaker.name);
   cache.set(speaker.name, p);
   try {
     return await p;