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>

tts_service.py

@@ -3,7 +3,7 @@
 Chatterbox TTS – lokaler HTTP-Service
 
 Start:
-    uvicorn tts_service:app --host 127.0.0.1 --port 8000
+    uvicorn tts_service:app --host 0.0.0.0 --port 9999
 
 Endpunkte:
     POST /speak   – Text in Warteschlange einreihen
@@ -178,8 +178,8 @@ class SpeakRequest(BaseModel):
     interrupt: bool = False
     speed: float = Field(default=1.0, ge=0.5, le=2.0)
     t3_model: str = "v3"
-    audio_device: str = "pulse"
-    max_len: int = Field(default=400, ge=50, le=1000)
+    audio_device: Optional[str] = None
+    max_len: int = Field(default=400, ge=100, le=1000)
     save_wav: bool = False
     output_path: Optional[str] = None
     session_id: Optional[str] = None