feat(voice_loop): --voice-Option + saubere Default-Stimme je TTS-Provider

- voice_loop.py: --voice reicht die Stimme im Start-Frame durch (nur wenn gesetzt),
  sonst greift der Provider-Default. Beispiele in Docstring/Help.
- ws.py/speak.py/chat.py: ohne explizite Stimme None durchreichen statt die
  OpenRouter-Stimme zu erzwingen -> jeder Provider nimmt SEINEN Default
  (OPENROUTER_TTS_VOICE bzw. PIPER_VOICE). Ungenutzten settings-Import in speak.py
  entfernt.
- Doku: BEDIENUNGSANLEITUNG (--voice + Default-Stimme je Provider).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/api/chat.py

@@ -51,7 +51,8 @@ async def chat(
         "llm_provider": payload.llm_provider,
         "tts_provider": payload.tts_provider,
     }
-    voice = payload.voice or settings.openrouter_tts_voice
+    # None -> der gewaehlte TTS-Provider nimmt seinen eigenen Default.
+    voice = payload.voice
 
     store = get_store()
 

app/api/speak.py

@@ -3,7 +3,6 @@ from io import BytesIO
 from fastapi import APIRouter, Depends, HTTPException, Query
 from fastapi.responses import StreamingResponse
 
-from app.config import settings
 from app.errors import RoutingError
 from app.auth import require_user
 from app.store import User, SessionOwnershipError
@@ -33,7 +32,8 @@ async def speak(
         "language": payload.language,
         "tts_provider": payload.tts_provider,
     }
-    voice = payload.voice or settings.openrouter_tts_voice
+    # None -> der gewaehlte TTS-Provider nimmt seinen eigenen Default.
+    voice = payload.voice
 
     try:
         route = resolve_route(user, session_id, overrides)

app/api/ws.py

@@ -90,7 +90,9 @@ async def _run_turn(websocket, store, user, session_id, route, orchestrator, out
 
     await websocket.send_json({"type": "ack", "route": route.as_dict()})
 
-    voice = options.get("voice") or settings.openrouter_tts_voice
+    # Ohne explizite Stimme None lassen -> jeder TTS-Provider nimmt SEINEN Default
+    # (OpenRouter: OPENROUTER_TTS_VOICE, piper: PIPER_VOICE).
+    voice = options.get("voice")
     stream = bool(options.get("stream"))
     # audio_stream: explizite Anfrage gewinnt, sonst der serverseitige Default (Admin).
     audio_stream = bool(options["audio_stream"]) if "audio_stream" in options \