services:
  faster-qwen3-tts:
    image: martinb78/faster-qwen3-tts-dgx-spark:latest
    container_name: faster-qwen3-tts
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      # Optional: set HF_TOKEN if model needs downloading from HuggingFace
      # - HF_TOKEN=${HF_TOKEN}
    ports:
      - "8020:8000"
    volumes:
      # Mount your local Qwen3-TTS model (download first, see README)
      - ${MODEL_PATH:-./models/Qwen3-TTS}:/models/Qwen3-TTS:ro
      # Config directory (voices.json generated on startup)
      - ./config:/config:rw
      # Speaker reference audio files
      - ./config/speakers:/voices:ro
    command: >
      /bin/bash -c "
      python3 /config/generate_voices.py &&
      python3 /config/run_server.py
      --model /models/Qwen3-TTS
      --voices /config/voices.json
      --port 8000
      --max-seq-len 2048
      "
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

networks:
  dgx_net:
    external: true