Add Qwen3-TTS zero-shot voice cloning web UI

Extract the voice-cloning feature from jamiepine/voicebox (Qwen3-TTS Base
engine) into a small standalone app: FastAPI backend (engine.py + app.py)
wrapping create_voice_clone_prompt/generate_voice_clone, and a single-page
UI (upload or mic-record a reference clip + transcript -> synthesize any
text in that voice). Supports 10 languages incl. Korean; model loads lazily
and downloads on first use.

app.py

@@ -0,0 +1,156 @@
+"""
+voice_copy — simple web UI for zero-shot voice cloning.
+
+Run:
+    python app.py            # then open http://localhost:8000
+    # or: uvicorn app:app --host 0.0.0.0 --port 8000
+
+Env:
+    VOICE_COPY_MODEL_SIZE   "1.7B" (default) or "0.6B"
+    VOICE_COPY_DEVICE       force "cuda" / "cpu" / "mps" (default: auto)
+    VOICE_COPY_HOST         bind host (default 0.0.0.0)
+    VOICE_COPY_PORT         bind port (default 8000)
+"""
+
+from __future__ import annotations
+
+import io
+import logging
+import os
+import tempfile
+from pathlib import Path
+
+import numpy as np
+import soundfile as sf
+from fastapi import FastAPI, File, Form, HTTPException, UploadFile
+from fastapi.concurrency import run_in_threadpool
+from fastapi.responses import HTMLResponse, Response
+
+from engine import HF_MODEL_MAP, LANGUAGE_CODE_TO_NAME, VoiceCloner
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(name)s: %(message)s")
+logger = logging.getLogger("voice_copy.app")
+
+BASE = Path(__file__).resolve().parent
+STATIC = BASE / "static"
+TMP = BASE / "tmp"
+TMP.mkdir(exist_ok=True)
+
+MODEL_SIZE = os.environ.get("VOICE_COPY_MODEL_SIZE", "1.7B")
+DEVICE = os.environ.get("VOICE_COPY_DEVICE") or None
+
+cloner = VoiceCloner(model_size=MODEL_SIZE, device=DEVICE)
+app = FastAPI(title="voice_copy", description="Zero-shot voice cloning UI")
+
+
+def _decode_to_wav(raw_bytes: bytes, filename: str) -> str:
+    """Decode uploaded audio (wav/flac/mp3/m4a/ogg/webm) into a mono wav on disk.
+
+    Tries soundfile first (wav/flac/ogg — no ffmpeg needed); falls back to
+    librosa/audioread (needs ffmpeg for mp3/m4a/webm from the mic recorder).
+    """
+    suffix = Path(filename or "ref").suffix or ".bin"
+    src = tempfile.NamedTemporaryFile(dir=TMP, suffix=suffix, delete=False)
+    src.write(raw_bytes)
+    src.close()
+
+    try:
+        try:
+            audio, sr = sf.read(src.name, dtype="float32", always_2d=False)
+            if audio.ndim > 1:  # stereo -> mono
+                audio = audio.mean(axis=1)
+        except Exception:
+            import librosa
+
+            audio, sr = librosa.load(src.name, sr=None, mono=True)
+    finally:
+        try:
+            os.unlink(src.name)
+        except OSError:
+            pass
+
+    wav = tempfile.NamedTemporaryFile(dir=TMP, suffix=".wav", delete=False)
+    wav.close()
+    sf.write(wav.name, np.asarray(audio, dtype=np.float32), int(sr), format="WAV")
+    return wav.name
+
+
+@app.get("/", response_class=HTMLResponse)
+def index() -> str:
+    return (STATIC / "index.html").read_text(encoding="utf-8")
+
+
+@app.get("/api/health")
+def health() -> dict:
+    return {
+        "device": cloner.device,
+        "model_size": cloner.model_size,
+        "model_repo": HF_MODEL_MAP[cloner.model_size],
+        "model_loaded": cloner.loaded,
+        "languages": list(LANGUAGE_CODE_TO_NAME.keys()),
+    }
+
+
+@app.post("/api/clone")
+async def clone(
+    ref_audio: UploadFile = File(...),
+    ref_text: str = Form(...),
+    text: str = Form(...),
+    language: str = Form("auto"),
+    instruct: str = Form(""),
+    seed: str = Form(""),
+) -> Response:
+    if not text.strip():
+        raise HTTPException(400, "합성할 텍스트(text)를 입력하세요.")
+    if not ref_text.strip():
+        raise HTTPException(400, "참조 오디오의 전사(ref_text)를 입력하세요.")
+
+    raw = await ref_audio.read()
+    if not raw:
+        raise HTTPException(400, "참조 오디오 파일이 비어 있습니다.")
+
+    seed_int = None
+    if seed.strip():
+        try:
+            seed_int = int(seed)
+        except ValueError:
+            raise HTTPException(400, "seed는 정수여야 합니다.")
+
+    try:
+        wav_path = await run_in_threadpool(_decode_to_wav, raw, ref_audio.filename or "ref.wav")
+    except Exception as exc:  # noqa: BLE001
+        logger.exception("audio decode failed")
+        raise HTTPException(
+            400,
+            f"오디오 디코딩 실패: {exc}. wav/flac는 그대로 되고, mp3/m4a/webm은 ffmpeg 설치가 필요합니다.",
+        )
+
+    try:
+        audio, sr = await run_in_threadpool(
+            cloner.clone, wav_path, ref_text, text, language, instruct or None, seed_int
+        )
+    except Exception as exc:  # noqa: BLE001
+        logger.exception("clone failed")
+        raise HTTPException(500, f"생성 실패: {exc}")
+    finally:
+        try:
+            os.unlink(wav_path)
+        except OSError:
+            pass
+
+    buf = io.BytesIO()
+    sf.write(buf, audio, sr, format="WAV")
+    buf.seek(0)
+    return Response(
+        content=buf.read(),
+        media_type="audio/wav",
+        headers={"Content-Disposition": 'inline; filename="cloned.wav"'},
+    )
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    host = os.environ.get("VOICE_COPY_HOST", "0.0.0.0")
+    port = int(os.environ.get("VOICE_COPY_PORT", "8000"))
+    uvicorn.run(app, host=host, port=port)