version: '3.8'

services:
  voicebox:
    image: ghcr.io/jamiepine/voicebox:latest-cuda
    container_name: voicebox
    restart: unless-stopped
    ports:
      - "8000:8000"
    volumes:
      - voicebox-data:/app/data
      - huggingface-cache:/root/.cache/huggingface
    environment:
      - GPU_MEMORY_FRACTION=0.8
      - LOG_LEVEL=info
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

volumes:
  voicebox-data:
    driver: local
  huggingface-cache:
    driver: local