Initial commit: Korean voice-cloning TTS prototype

FastAPI backend, web UI, CosyVoice3/F5-TTS setup scripts, and handoff docs for GPU PC continuation.

Co-authored-by: Cursor <cursoragent@cursor.com>

scripts/prepare_reference.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+# reference WAV를 mono 24kHz로 정규화
+set -euo pipefail
+
+if [[ $# -lt 1 ]]; then
+  echo "Usage: $0 input.wav [output.wav]"
+  exit 1
+fi
+
+IN="$1"
+OUT="${2:-${IN%.wav}_24k_mono.wav}"
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+PY="${ROOT}/.venvs/api/bin/python"
+if [[ ! -x "$PY" ]]; then
+  PY=python3
+fi
+
+"$PY" - <<PY
+import sys
+try:
+    import soundfile as sf
+    import numpy as np
+except ImportError:
+    print("soundfile 필요: pip install soundfile")
+    sys.exit(1)
+
+data, sr = sf.read("$IN", always_2d=False)
+if data.ndim > 1:
+    data = data.mean(axis=1)
+target_sr = 24000
+if sr != target_sr:
+    import librosa
+    data = librosa.resample(data.astype(float), orig_sr=sr, target_sr=target_sr)
+    sr = target_sr
+sf.write("$OUT", data, sr, subtype="PCM_16")
+print(f"Saved: $OUT ({sr} Hz mono)")
+PY