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>

docker-compose.yml

@@ -0,0 +1,28 @@
+# NVIDIA GPU 서버용 (모델 venv는 호스트에서 setup 후 볼륨 마운트 권장)
+services:
+  tts-api:
+    image: nvidia/cuda:12.4.1-runtime-ubuntu22.04
+    working_dir: /app
+    volumes:
+      - .:/app
+      - ./.venvs:/app/.venvs
+      - ./models:/app/models
+      - ./samples:/app/samples
+      - ./outputs:/app/outputs
+    ports:
+      - "8000:8000"
+    environment:
+      - TTS_MODEL=cosyvoice
+      - PYTHONPATH=/app
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    command: >
+      bash -c "
+        apt-get update -qq && apt-get install -y -qq python3 python3-venv python3-pip sox libsox-dev ffmpeg git &&
+        ./scripts/run_server.sh
+      "