Add HTTP service, MCP adapter, systemd autostart; fix bugs and docs

- chatterbox_cli_v4.py: cooperative stop/interrupt via threading.Event;
  fix force_split_sentence (word boundary instead of mid-word cut);
  fix synthesize_streaming normalization order (split before preprocess)
- tts_service.py: FastAPI service with job queue, model cache, worker thread;
  LAN-accessible on 0.0.0.0:9999; audio_device default None (auto)
- mcp_adapter.py: MCP adapter (stdio + streamable-http) wrapping REST API;
  update docstring and default TTS_URL to port 9999
- requirements.txt: add fastapi, uvicorn, httpx, mcp
- README.md, BEDIENUNGSANLEITUNG.md: document service, MCP, AI integrations
  (Claude, Ollama, Open WebUI, llama.cpp, Home Assistant), systemd autostart
- CLAUDE.md: reflect current architecture (service + adapter now implemented)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

requirements.txt

@@ -1,27 +1,25 @@
 # Chatterbox TTS CLI — Abhängigkeiten
 # Getestet mit Python 3.11, CUDA 12.x, Ubuntu 22.04/24.04
+#
+# PyTorch separat installieren (passende CUDA-Version via pytorch.org):
+#   pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu124
 
-# TTS-Kern
+# --- TTS-Kern ---
 chatterbox-tts>=0.1.7
 
-# PyTorch (passende CUDA-Version separat installieren, z. B. via pytorch.org)
-torch>=2.6.0
-torchaudio>=2.6.0
-
-# Audio-Ausgabe (Linux/PipeWire/PulseAudio)
+# --- Audio-Ausgabe (Linux/PipeWire/PulseAudio) ---
 sounddevice>=0.4.0
 
-# Pitch-erhaltende Zeitstreckung (Geschwindigkeitsanpassung)
+# --- Pitch-erhaltende Zeitstreckung (--speed != 1.0) ---
+# Systempaket zusätzlich erforderlich: sudo apt install rubberband-cli
 pyrubberband>=0.4.0
-# rubberband-cli muss zusätzlich als Systempakete installiert sein:
-#   sudo apt install rubberband-cli
 
-# HTTP-Service (Phase 2)
+# --- HTTP-Service (tts_service.py) ---
 fastapi>=0.115.0
 uvicorn[standard]>=0.32.0
 
-# HTTP-Client für MCP-Adapter (Phase 3)
+# --- HTTP-Client (mcp_adapter.py → tts_service.py) ---
 httpx>=0.28.0
 
-# MCP-Adapter (Phase 3)
+# --- MCP-Adapter (mcp_adapter.py) ---
 mcp>=1.0.0