Add TTS/STT service with Coqui TTS and faster-whisper

- Added tts-stt service definition to docker-compose.yml
- Created tts-stt directory with:
  - Dockerfile: Based on debian:trixie-slim with ROCm dependencies
  - requirements.txt: Python packages including TTS, faster-whisper, FastAPI
  - app.py: FastAPI service with /tts and /stt endpoints
- Service includes GPU device mapping (/dev/kfd, /dev/dri) for ROCm acceleration
- Uses YourTTS multilingual model for TTS and large-v3 for Whisper
- Configured to use persistent storage for models and cache

ai/compose.yml

@@ -81,6 +81,29 @@ services:
       - "303"
       - "26"
 
+
+  tts-stt:
+    build:
+      context: ./tts-stt
+      dockerfile: Dockerfile
+    container_name: tts-stt
+    restart: always
+    volumes:
+      - /mnt/HoardingCow_docker_data/TTS-Stt/models:/app/models
+      - /mnt/HoardingCow_docker_data/TTS-Stt/cache:/app/cache
+    environment:
+      - TTS_MODEL=tts_models/multilingual/multi-dataset/your_tts
+      - WHISPER_MODEL=large-v3
+      - DEVICE=cuda
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri:/dev/dri
+    group_add:
+      - "303"
+      - "26"
+    networks:
+      - ai_backend
+
 networks:
   ai_net:
     external: true