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>

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:
@@ -126,24 +127,24 @@ class VoiceCloner:
         self.load()
         import torch
 
-        if seed is not None:
-            torch.manual_seed(seed)
-            if self.device == "cuda":
-                torch.cuda.manual_seed_all(seed)
+        with self._gen_lock:
+            if seed is not None:
+                torch.manual_seed(seed)
+                if self.device == "cuda":
+                    torch.cuda.manual_seed_all(seed)
 
-        # Build the speaker prompt from the reference clip + its transcript.
-        voice_prompt = self.model.create_voice_clone_prompt(
-            ref_audio=str(ref_audio_path),
-            ref_text=ref_text,
-            x_vector_only_mode=False,
-        )
+            # Build the speaker prompt from the reference clip + its transcript.
+            voice_prompt = self.model.create_voice_clone_prompt(
+                ref_audio=str(ref_audio_path),
+                ref_text=ref_text,
+                x_vector_only_mode=False,
+            )
 
-        wavs, sample_rate = self.model.generate_voice_clone(
-            text=text,
-            voice_clone_prompt=voice_prompt,
-            language=LANGUAGE_CODE_TO_NAME.get(language, "auto"),
-            instruct=instruct or None,
-        )
+            wavs, sample_rate = self.model.generate_voice_clone(
+                text=text,
+                voice_clone_prompt=voice_prompt,
+                language=LANGUAGE_CODE_TO_NAME.get(language, "auto"),
+            )
 
         audio = wavs[0]
         if isinstance(audio, torch.Tensor):