feat: FRIDAY Voice stack on the GPU machine; VoiceCoach history

FRIDAY Voice (speaches GPU STT/TTS + hermes agent + push-to-talk console) on .150 Docker Desktop, fronted by coach.hobbs.farm. Also captures the VoiceCoach compose/agent trees and deploy notes it replaced, which had never been committed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-11 11:19:04 -05:00
parent dddc6734d0
commit 266ea11447
29 changed files with 4494 additions and 0 deletions
@@ -0,0 +1,184 @@
+services:
+
+  # LiveKit WebRTC Server (unchanged)
+  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
+    dns_search: [""]
+    networks:
+      - voicecoach
+    mem_limit: 512M
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # Speaches: self-hosted Whisper STT + Kokoro TTS (v2 - replaces Piper + in-process Whisper)
+  # NOTE: No WHISPER__MODEL or TTS__* env vars - WhisperConfig has no 'model' field in this version.
+  # Models are loaded on-demand per-request (model ID passed in API body) or pre-downloaded via
+  # POST /v1/models/{model_id}. TTS model/voice are also per-request in POST /v1/audio/speech body.
+  # Volume must map to /home/ubuntu/.cache (container runs as 'ubuntu', not root).
+  speaches:
+    image: ghcr.io/speaches-ai/speaches:latest-cpu
+    container_name: voicecoach-speaches
+    restart: unless-stopped
+    environment:
+      - WHISPER__INFERENCE_DEVICE=cpu
+      - WHISPER__COMPUTE_TYPE=int8
+      - WHISPER__TTL=-1
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/speaches-models:/home/ubuntu/.cache
+    dns_search: [""]
+    networks:
+      - voicecoach
+    mem_limit: 3G
+    memswap_limit: 3G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    healthcheck:
+      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 120s
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # SpeechBrain Emotion Analysis (unchanged, internal only)
+  speechbrain-service:
+    build:
+      context: ./speechbrain-service
+    image: voicecoach-speechbrain:latest
+    container_name: voicecoach-speechbrain
+    restart: unless-stopped
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/speechbrain-models:/app/models
+      - /mnt/docker-data/configs/voicecoach/clips:/data/clips
+    environment:
+      - MODEL_DIR=/app/models
+    dns_search: [""]
+    networks:
+      - voicecoach
+    mem_limit: 3G
+    memswap_limit: 3G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # OpenClaw VoiceCoach Agent (v2 - LLM gateway with memory/skills)
+  voicecoach-openclaw:
+    image: margaret-openclaw:latest
+    container_name: voicecoach-openclaw
+    restart: unless-stopped
+    user: "0:0"
+    ports:
+      - "3100:3100"
+    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:
+      - /mnt/infrastructure/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"]
+    dns_search: [""]
+    networks:
+      - voicecoach
+    mem_limit: 2G
+    memswap_limit: 2G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # Pipecat Voice Pipeline Agent (v2 - uses Speaches + OpenClaw gateway)
+  pipecat-agent:
+    build:
+      context: ./pipecat-agent
+    image: voicecoach-pipecat:latest
+    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://192.168.86.150:8000
+      - SPEECHBRAIN_URL=http://speechbrain-service:8001
+      - OPENCLAW_URL=http://voicecoach-openclaw:3100
+      - OPENCLAW_AGENT_ID=voicecoach
+      - WHISPER_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
+      - KOKORO_VOICE=af_nova
+      - CLIPS_DIR=/data/clips/pending
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/clips:/data/clips
+    depends_on:
+      - livekit-server
+      - speechbrain-service
+      - voicecoach-openclaw
+    dns_search: [""]
+    networks:
+      - voicecoach
+    mem_limit: 1G
+    memswap_limit: 1G
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # Web Client (unchanged)
+  voicecoach-web:
+    build:
+      context: ./web-client
+    image: voicecoach-web:latest
+    container_name: voicecoach-web
+    restart: unless-stopped
+    ports:
+      - "8085:80"
+    depends_on:
+      - pipecat-agent
+    dns_search: [""]
+    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