tts-dgx-spark-faster-qwen3-tts/docker/docker-compose.portainer-0.6b.yml

# ─────────────────────────────────────────────────────────────────────────────
#  Qwen3-TTS GPU Stack
#
#  Ports:
#    8020 -> Voice clone, OpenAI-compatible /v1/audio/speech 
#    8021 -> VoiceDesign model for prompt-designed voices
#    8022 -> CustomVoice model
#    8023 -> Low-latency streaming voice clone endpoint 
#
#  Container Name	            RAM Usage	GPU VRAM Usage
#  faster-qwen3-tts-voiceclone	~2.72 GiB	5327 MiB (~5.2 GiB)
#  faster-qwen3-tts-customvoice	~2.88 GiB	4683 MiB (~4.6 GiB)
#  faster-qwen3-tts-voicedesign	~2.90 GiB	4747 MiB (~4.6 GiB)
#  faster-qwen3-tts-streaming	~2.54 GiB	5659 MiB (~5.5 GiB)
#
#  Voice files:
#    The voice clone and streaming services scan active voices from:
#    home/sparky/Media/_Sounds/TTS_Voices/active_voices
#
#  Portainer note:
#    Set HF_TOKEN in the stack environment if the models ever need Hugging Face access.
# ─────────────────────────────────────────────────────────────────────────────

services:
  # Standard voice cloning backend used by TTS Voice Creator and other OpenAI-compatible clients.
  faster-qwen3-tts-voiceclone:
    image: martinb78/faster-qwen3-tts-dgx-spark:latest
    container_name: tts-faster-qwen3-tts-voiceclone
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
      - EMBED_TAG=1.7b
    ports:
      - "8020:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-Base:/models/Qwen3-TTS:ro
      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
      - /home/sparky/Media/_Sounds/TTS_Voices/active_voices:/voices:rw
    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 4096
      "      
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

  # VoiceDesign backend: creates speech from a descriptive voice prompt instead of a reference clip.
  faster-qwen3-tts-voicedesign:
    image: martinb78/faster-qwen3-tts-dgx-spark:latest
    container_name: tts-faster-qwen3-tts-voicedesign
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
    ports:
      - "8021:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-VoiceDesign:/models/Qwen3-TTS-VoiceDesign:ro
      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
    command: >
      /bin/bash -c "
      python3 /config/run_voicedesign_server.py
      --model /models/Qwen3-TTS-VoiceDesign
      --voices /config/voicedesign_voices.json
      --port 8000
      --max-seq-len 2048
      "      
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

  # CustomVoice backend: keeps the separate CustomVoice model available on port 8022.
  faster-qwen3-tts-customvoice:
    image: martinb78/faster-qwen3-tts-dgx-spark:latest
    container_name: tts-faster-qwen3-tts-customvoice
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
    ports:
      - "8022:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-CustomVoice:/models/Qwen3-TTS-CustomVoice:ro
      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
    command: >
      /bin/bash -c "
      python3 /config/run_customvoice_server.py
      --model /models/Qwen3-TTS-CustomVoice
      --voices /config/customvoice_voices.json
      --port 8000
      --max-seq-len 2048
      "      
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

  # Streaming voice clone backend: same active voices as 8020, but streams WAV chunks while generating.
  faster-qwen3-tts-streaming:
    image: martinb78/faster-qwen3-tts-dgx-spark:latest-streaming
    container_name: tts-faster-qwen3-tts-streaming
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
      - EMBED_TAG=0.6b
    ports:
      - "8023:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-0.6B-Base:/models/Qwen3-TTS:ro
      - /home/sparky/Docker/tts-dgx-spark-faster-qwen3-tts/config:/config:rw
      - /home/sparky/Media/_Sounds/TTS_Voices/active_voices:/voices:rw
    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