voicecoach/docker-compose.yml

services:

  # LiveKit WebRTC Server
  livekit-server:
    image: livekit/livekit-server:latest
    container_name: voicecoach-livekit
    restart: unless-stopped
    command:
      - --config
      - /etc/livekit/livekit.yaml
      - --keys
      - "${LIVEKIT_API_KEY}: ${LIVEKIT_API_SECRET}"
    ports:
      - "7880:7880"
      - "7881:7881"
      - "50000-50100:50000-50100/udp"
    volumes:
      - ./livekit/livekit.yaml:/etc/livekit/livekit.yaml:ro
    networks:
      - voicecoach
    mem_limit: 512M
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # Speaches: GPU-accelerated Whisper STT + Kokoro TTS
  speaches:
    image: ghcr.io/speaches-ai/speaches:latest-cuda
    container_name: voicecoach-speaches-gpu
    restart: unless-stopped
    environment:
      - WHISPER__INFERENCE_DEVICE=cuda
      - WHISPER__COMPUTE_TYPE=float16
      - WHISPER__TTL=-1
    volumes:
      - speaches-models:/home/ubuntu/.cache
    networks:
      - voicecoach
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    mem_limit: 4G
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # SpeechBrain Emotion Analysis
  speechbrain-service:
    image: voicecoach-speechbrain:latest
    build:
      context: ./speechbrain-service
    container_name: voicecoach-speechbrain
    restart: unless-stopped
    volumes:
      - speechbrain-models:/app/models
      - voicecoach-clips:/data/clips
    environment:
      - MODEL_DIR=/app/models
    networks:
      - voicecoach
    mem_limit: 3G
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # OpenClaw VoiceCoach Agent (LLM gateway -> Claude)
  voicecoach-openclaw:
    image: margaret-openclaw:latest
    container_name: voicecoach-openclaw
    restart: unless-stopped
    user: "0:0"
    environment:
      - NODE_ENV=production
      - HOME=/home/glyptic
      - USER=glyptic
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - OPENCLAW_STATE_DIR=/home/glyptic/.voicecoach
      - OPENCLAW_CONFIG_PATH=/home/glyptic/.voicecoach/openclaw.json
    volumes:
      - ./voicecoach:/home/glyptic/.voicecoach
    command: ["sh", "-c", "mkdir -p /home/glyptic && node --max-old-space-size=1500 /usr/local/lib/node_modules/openclaw/dist/index.js gateway --allow-unconfigured"]
    networks:
      - voicecoach
    mem_limit: 2G
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # Pipecat Voice Pipeline Agent
  pipecat-agent:
    image: voicecoach-pipecat:latest
    build:
      context: ./pipecat-agent
    container_name: voicecoach-pipecat
    restart: unless-stopped
    env_file:
      - .env
    environment:
      - LIVEKIT_URL=ws://livekit-server:7880
      - LIVEKIT_PUBLIC_URL=wss://voice.hobbs.farm
      - SPEACHES_URL=http://speaches:8000
      - SPEECHBRAIN_URL=http://speechbrain-service:8001
      - LLM_BASE_URL=http://host.docker.internal:11434/v1
      - LLM_MODEL=llama3.1:8b
      - WHISPER_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
      - KOKORO_VOICE=af_nova
      - CLIPS_DIR=/data/clips/pending
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - voicecoach-clips:/data/clips
    depends_on:
      - livekit-server
      - speaches
      - speechbrain-service
    networks:
      - voicecoach
    mem_limit: 1G
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # Token Server + Settings API (separate from pipeline so it never goes down)
  token-server:
    image: voicecoach-pipecat:latest
    container_name: voicecoach-token-server
    restart: unless-stopped
    env_file:
      - .env
    environment:
      - LIVEKIT_PUBLIC_URL=wss://voice.hobbs.farm
      - SETTINGS_PATH=/data/settings.json
    command: ["python", "token_server.py"]
    volumes:
      - voicecoach-settings:/data
    networks:
      - voicecoach
    mem_limit: 256M
    healthcheck:
      test: ["CMD", "python", "-c", "import httpx; httpx.get('http://localhost:8080/health').raise_for_status()"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # Web Client
  voicecoach-web:
    image: voicecoach-web:latest
    build:
      context: ./web-client
    container_name: voicecoach-web
    restart: unless-stopped
    ports:
      - "8085:80"
    depends_on:
      - token-server
    networks:
      - voicecoach
    mem_limit: 128M
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

networks:
  voicecoach:
    driver: bridge

volumes:
  speaches-models:
  speechbrain-models:
  voicecoach-clips:
  voicecoach-settings: