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/select_model.sh

@@ -0,0 +1,34 @@
+#!/usr/bin/env bash
+# 최종 모델 선택을 .env 와 config에 반영
+set -euo pipefail
+
+MODEL="${1:-}"
+if [[ -z "$MODEL" || ! "$MODEL" =~ ^(cosyvoice|f5_tts)$ ]]; then
+  echo "Usage: $0 cosyvoice|f5_tts"
+  exit 1
+fi
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+ENV_FILE="$ROOT/.env"
+
+if [[ -f "$ENV_FILE" ]]; then
+  if grep -q '^TTS_MODEL=' "$ENV_FILE"; then
+    sed -i.bak "s/^TTS_MODEL=.*/TTS_MODEL=$MODEL/" "$ENV_FILE"
+    rm -f "$ENV_FILE.bak"
+  else
+    echo "TTS_MODEL=$MODEL" >> "$ENV_FILE"
+  fi
+else
+  cp "$ROOT/.env.example" "$ENV_FILE"
+  echo "TTS_MODEL=$MODEL" >> "$ENV_FILE"
+fi
+
+python3 - <<PY
+import json
+from pathlib import Path
+p = Path("$ROOT/config/model_choice.json")
+data = json.loads(p.read_text(encoding="utf-8"))
+data["selected_model"] = "$MODEL"
+p.write_text(json.dumps(data, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
+print("selected_model=$MODEL")
+PY