feat: initial commit — VoiceCoach real-time voice coaching pipeline

Services: Pipecat agent (LiveKit + Claude + Whisper STT + Piper TTS), SpeechBrain analysis service, Piper TTS service, web client (nginx). Includes LiveKit server config and docker-compose orchestration. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-01 01:15:24 -05:00
commit 59856bd4fc
23 changed files with 1209 additions and 0 deletions
@@ -0,0 +1,127 @@
+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"
+
+  # SpeechBrain Emotion Analysis (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
+    environment:
+      - MODEL_DIR=/app/models
+    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"
+
+  # Piper TTS (internal only)
+  piper-tts:
+    build:
+      context: ./piper-service
+    image: voicecoach-piper:latest
+    container_name: voicecoach-piper
+    restart: unless-stopped
+    environment:
+      - PIPER_MODEL=/app/models/en_US-lessac-medium.onnx
+    networks:
+      - voicecoach
+    mem_limit: 512M
+    labels:
+      - "com.centurylinklabs.watchtower.enable=false"
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "50m"
+        max-file: "3"
+
+  # Pipecat Voice Pipeline Agent
+  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
+      - SPEECHBRAIN_SERVICE_URL=http://speechbrain-service:8001
+      - PIPER_SERVICE_URL=http://piper-tts:8003
+      - WHISPER_MODEL=medium
+    depends_on:
+      - livekit-server
+      - speechbrain-service
+      - piper-tts
+    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"
+
+  # Web Client (phone interface)
+  voicecoach-web:
+    build:
+      context: ./web-client
+    image: voicecoach-web:latest
+    container_name: voicecoach-web
+    restart: unless-stopped
+    ports:
+      - "8085:80"
+    depends_on:
+      - pipecat-agent
+    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