Fix clone API: drop no-op instruct, serialize generation, clearer errors

- Remove the 'instruct' style field: Qwen3-TTS Base generate_voice_clone
  silently ignores it, so the UI option did nothing.
- Serialize generations with a lock so concurrent requests queue instead
  of doubling RAM/VRAM on one shared model.
- Validate empty text/ref_text ourselves so the API returns the Korean
  400 messages instead of FastAPI's generic 422.
- UI: explain that mic recording needs https/localhost instead of a raw
  TypeError on plain-http LAN access.
- README: document mic/https limit, queueing, and measured CPU speed.

Verified on CPU (Python 3.12, torch 2.14 CPU, 0.6B Base): wav and mp3
references, language ko/auto, two concurrent requests -> all 200 and
Whisper transcripts match the requested text.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

README.md

@@ -51,10 +51,15 @@ python app.py
 2. **전사** — 그 참조 음성에서 말한 내용을 그대로 텍스트로 적습니다. (클로닝 품질에 중요)
 3. **합성할 텍스트** — 그 목소리로 말하게 할 문장을 입력하고 "목소리 생성"을 누릅니다.
 
+- 마이크 녹음은 브라우저 보안 정책상 `http://localhost` 또는 `https://` 접속에서만 동작합니다.
+  다른 PC에서 `http://<서버IP>:8000`으로 접속했다면 녹음 대신 파일 업로드를 사용하세요.
+- 생성 요청은 한 번에 하나씩 순서대로 처리됩니다(동시 요청 시 대기).
+- 참고 속도: CPU(8코어)·0.6B 모델 기준 짧은 한 문장에 수십 초~1분대(호스트 부하에 따라 다름). GPU에서는 훨씬 빠릅니다.
+
 ## API
 
 - `GET /api/health` — 디바이스/모델/언어 상태
-- `POST /api/clone` — multipart form: `ref_audio`(파일), `ref_text`, `text`, `language`, `instruct`(선택), `seed`(선택) → `audio/wav` 반환
+- `POST /api/clone` — multipart form: `ref_audio`(파일), `ref_text`, `text`, `language`, `seed`(선택) → `audio/wav` 반환
 
 ```bash
 curl -X POST http://localhost:8000/api/clone \

app.py

@@ -94,10 +94,9 @@ def health() -> dict:
 @app.post("/api/clone")
 async def clone(
     ref_audio: UploadFile = File(...),
-    ref_text: str = Form(...),
+    ref_text: str = Form(""),
-    text: str = Form(...),
+    text: str = Form(""),
     language: str = Form("auto"),
-    instruct: str = Form(""),
     seed: str = Form(""),
 ) -> Response:
     if not text.strip():
@@ -127,7 +126,7 @@ async def clone(
 
     try:
         audio, sr = await run_in_threadpool(
-            cloner.clone, wav_path, ref_text, text, language, instruct or None, seed_int
+            cloner.clone, wav_path, ref_text.strip(), text.strip(), language, seed_int
         )
     except Exception as exc:  # noqa: BLE001
         logger.exception("clone failed")

engine.py

@@ -69,6 +69,9 @@ class VoiceCloner:
         self.model_size = model_size
         self.device = device or pick_device()
         self._lock = threading.Lock()
+        # One generation at a time: the model is shared and a second concurrent
+        # run would just double VRAM/RAM use (and can OOM a small GPU).
+        self._gen_lock = threading.Lock()
 
     @property
     def loaded(self) -> bool:
@@ -107,7 +110,6 @@ class VoiceCloner:
         ref_text: str,
         text: str,
         language: str = "auto",
-        instruct: Optional[str] = None,
         seed: Optional[int] = None,
     ) -> Tuple[np.ndarray, int]:
         """Synthesize `text` in the voice of `ref_audio_path`.
@@ -117,7 +119,6 @@ class VoiceCloner:
             ref_text: Exact transcript of the reference clip.
             text: The text to speak in the cloned voice.
             language: Language code from LANGUAGE_CODE_TO_NAME ("auto" to detect).
-            instruct: Optional natural-language style hint (e.g. "speak cheerfully").
             seed: Optional random seed for reproducible output.
 
         Returns:
@@ -126,6 +127,7 @@ class VoiceCloner:
         self.load()
         import torch
 
+        with self._gen_lock:
             if seed is not None:
                 torch.manual_seed(seed)
                 if self.device == "cuda":
@@ -142,7 +144,6 @@ class VoiceCloner:
                 text=text,
                 voice_clone_prompt=voice_prompt,
                 language=LANGUAGE_CODE_TO_NAME.get(language, "auto"),
-            instruct=instruct or None,
             )
 
         audio = wavs[0]

static/index.html

@@ -66,10 +66,6 @@
         <label>언어</label>
         <select id="language"></select>
       </div>
-      <div>
-        <label>스타일 지시 <span class="hint">(선택)</span></label>
-        <input type="text" id="instruct" placeholder="예) 밝고 활기차게" />
-      </div>
       <div>
         <label>seed <span class="hint">(선택)</span></label>
         <input type="number" id="seed" placeholder="랜덤" />
@@ -119,6 +115,10 @@ $("file").addEventListener("change", () => {
 
 // ── Mic recording → in-browser WAV (no ffmpeg needed) ──
 $("recBtn").addEventListener("click", async () => {
+  if (!window.isSecureContext || !navigator.mediaDevices) {
+    setStatus("브라우저 보안 정책상 마이크 녹음은 https 또는 localhost 접속에서만 됩니다. 녹음 파일을 업로드해 주세요.", "err");
+    return;
+  }
   try {
     stream = await navigator.mediaDevices.getUserMedia({ audio: true });
   } catch (e) { setStatus("마이크 접근 실패: " + e.message, "err"); return; }
@@ -179,7 +179,6 @@ $("go").addEventListener("click", async () => {
   fd.append("ref_text", refText);
   fd.append("text", text);
   fd.append("language", $("language").value);
-  fd.append("instruct", $("instruct").value.trim());
   fd.append("seed", $("seed").value.trim());
 
   $("go").disabled = true;