feat: VoiceCoach v2 - OpenClaw gateway + Speaches STT/TTS

- pipeline.py: completely rewritten to use Speaches STT/TTS and OpenClaw LLM
- main.py: v2 with OPENCLAW_TOKEN support
- requirements.txt: slimmed (removed anthropic, faster-whisper direct deps)
- Dockerfile: slimmer build (no model pre-download)
- whisper_stt.py, piper_tts.py: removed (replaced by Speaches API)
- docker-compose.yml: v2 with speaches + openclaw services, piper-tts removed
- openclaw-agent/system_prompt.md: new directory with agent system prompt

docker-compose.yml

@@ -1,6 +1,6 @@
 services:
 
-  # LiveKit WebRTC Server
+  # LiveKit WebRTC Server (unchanged)
   livekit-server:
     image: livekit/livekit-server:latest
     container_name: voicecoach-livekit
@@ -27,7 +27,39 @@ services:
         max-size: "50m"
         max-file: "3"
 
-  # SpeechBrain Emotion Analysis (internal only)
+  # Speaches: self-hosted Whisper STT + Kokoro TTS (v2 - replaces Piper + in-process Whisper)
+  speaches:
+    image: ghcr.io/speaches-ai/speaches:latest-cpu
+    container_name: voicecoach-speaches
+    restart: unless-stopped
+    environment:
+      - WHISPER__MODEL=Systran/faster-whisper-large-v3-turbo
+      - WHISPER__INFERENCE_DEVICE=cpu
+      - WHISPER__COMPUTE_TYPE=int8
+      - TTS__MODEL=kokoro
+      - TTS__DEFAULT_VOICE=af_nova
+      - TTS__LANGUAGE=en-us
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/speaches-models:/root/.cache
+    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
@@ -36,6 +68,7 @@ services:
     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
     networks:
@@ -50,18 +83,26 @@ services:
         max-size: "50m"
         max-file: "3"
 
-  # Piper TTS (internal only)
-  piper-tts:
-    build:
-      context: ./piper-service
-    image: voicecoach-piper:latest
-    container_name: voicecoach-piper
+  # 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"
     environment:
-      - PIPER_MODEL=/app/models/en_US-lessac-medium.onnx
+      - 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"]
     networks:
       - voicecoach
-    mem_limit: 512M
+    mem_limit: 2G
+    memswap_limit: 2G
     labels:
       - "com.centurylinklabs.watchtower.enable=false"
     logging:
@@ -70,7 +111,7 @@ services:
         max-size: "50m"
         max-file: "3"
 
-  # Pipecat Voice Pipeline Agent
+  # Pipecat Voice Pipeline Agent (v2 - uses Speaches + OpenClaw gateway)
   pipecat-agent:
     build:
       context: ./pipecat-agent
@@ -81,18 +122,25 @@ services:
       - .env
     environment:
       - LIVEKIT_URL=ws://livekit-server:7880
-      - SPEECHBRAIN_SERVICE_URL=http://speechbrain-service:8001
-      - PIPER_SERVICE_URL=http://piper-tts:8003
-      - WHISPER_MODEL=medium
       - LIVEKIT_PUBLIC_URL=wss://voice.hobbs.farm
+      - SPEACHES_URL=http://speaches:8000
+      - SPEECHBRAIN_URL=http://speechbrain-service:8001
+      - OPENCLAW_URL=http://voicecoach-openclaw:3100
+      - OPENCLAW_AGENT_ID=voicecoach
+      - WHISPER_MODEL=Systran/faster-whisper-large-v3-turbo
+      - KOKORO_VOICE=af_nova
+      - CLIPS_DIR=/data/clips/pending
+    volumes:
+      - /mnt/docker-data/configs/voicecoach/clips:/data/clips
     depends_on:
       - livekit-server
+      - speaches
       - speechbrain-service
-      - piper-tts
+      - voicecoach-openclaw
     networks:
       - voicecoach
-    mem_limit: 3G
-    memswap_limit: 3G
+    mem_limit: 1G
+    memswap_limit: 1G
     labels:
       - "com.centurylinklabs.watchtower.enable=false"
     logging:
@@ -101,7 +149,7 @@ services:
         max-size: "50m"
         max-file: "3"
 
-  # Web Client (phone interface)
+  # Web Client (unchanged)
   voicecoach-web:
     build:
       context: ./web-client