Jamulix: Optimierungen übernehmen, lokale Voice-Modelle ignorieren

app/api/chat.py

@@ -13,6 +13,7 @@ from app.dependencies import (
     resolve_output_endpoint,
     get_store,
     piper_voice_for_language,
+    voice_for_route,
 )
 from app.core.memory_extractor import maybe_schedule_extraction
 from app.quota import enforce_quota, record_usage, QuotaExceededError
@@ -96,7 +97,7 @@ async def chat(
             raise HTTPException(status_code=429, detail=str(exc))
 
     # Explizit angeforderte Stimme gewinnt; sonst folgt sie der Routensprache.
-    voice = payload.voice or piper_voice_for_language(route.tts_provider, route.language)
+    voice = payload.voice or voice_for_route(route.tts_provider, route.language, route.voice_gender)
 
     try:
         trace, audio = await orchestrator.chat_text(

app/api/config.py

@@ -1,3 +1,4 @@
+import httpx
 from fastapi import APIRouter
 
 from app.config import settings, active_profile
@@ -12,14 +13,60 @@ from app.dependencies import (
 router = APIRouter()
 
 
+async def _chatterbox_reachable() -> bool:
+    try:
+        async with httpx.AsyncClient(timeout=1.5) as client:
+            r = await client.get(f"{settings.chatterbox_base_url.rstrip('/')}/status")
+            return r.status_code < 500
+    except Exception:
+        return False
+
+
+async def _cartesia_available() -> bool:
+    key = settings.cartesia_api_key.strip()
+    voice_id = settings.cartesia_voice_id.strip()
+    if not key or not voice_id:
+        return False
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            r = await client.get(
+                "https://api.cartesia.ai/voices",
+                headers={"X-API-Key": key, "Cartesia-Version": "2024-06-10"},
+            )
+            return r.status_code < 400
+    except Exception:
+        return False
+
+
+async def _openrouter_tts_available() -> bool:
+    """Prüft ob das konfigurierte TTS-Modell auf OpenRouter via /audio/speech erreichbar ist."""
+    key = settings.openrouter_api_key.strip()
+    model = settings.openrouter_tts_model.strip()
+    if not key or not model:
+        return False
+    try:
+        async with httpx.AsyncClient(timeout=5.0) as client:
+            r = await client.post(
+                "https://openrouter.ai/api/v1/audio/speech",
+                headers={"Authorization": f"Bearer {key}", "Content-Type": "application/json"},
+                json={"model": model, "input": "Test", "voice": settings.openrouter_tts_voice or "alloy",
+                      "response_format": "mp3"},
+            )
+            # 200 = Audio OK, 4xx mit "does not exist" = Modell fehlt
+            if r.status_code == 200:
+                return True
+            body = r.text
+            return "does not exist" not in body and r.status_code < 500
+    except Exception:
+        return False
+
+
 @router.get("/config")
 async def get_config():
-    """Zeigt aktives Profil, aufgeloeste Default-Route und verfuegbare Bausteine.
-
-    Bewusst OHNE Secrets - API-Keys werden nur als 'gesetzt/nicht gesetzt' gemeldet.
-    """
+    """Zeigt aktives Profil, aufgeloeste Default-Route und verfuegbare Bausteine."""
     route = resolve_route()
     audio_router = get_audio_router()
+    chatterbox_ok, openrouter_tts_ok, cartesia_ok = await _chatterbox_reachable(), await _openrouter_tts_available(), await _cartesia_available()
     return {
         "profile": active_profile(),
         "app_env": settings.app_env,
@@ -30,6 +77,9 @@ async def get_config():
             "tts_providers": sorted(TTS_REGISTRY),
             "input_endpoints": [c.model_dump() for c in await audio_router.list_inputs()],
             "output_endpoints": [c.model_dump() for c in await audio_router.list_outputs()],
+            "chatterbox_reachable": chatterbox_ok,
+            "openrouter_tts_available": openrouter_tts_ok,
+            "cartesia_available": cartesia_ok,
         },
         "secrets": {
             "openrouter_api_key_set": bool(settings.openrouter_api_key.strip()),

app/api/speak.py

@@ -12,6 +12,7 @@ from app.dependencies import (
     resolve_output_endpoint,
     get_store,
     piper_voice_for_language,
+    voice_for_route,
 )
 from app.quota import enforce_quota, record_usage, QuotaExceededError
 from app.schemas import SpeakRequest
@@ -36,7 +37,7 @@ async def speak(
     try:
         route = resolve_route(user, session_id, overrides)
         # Explizit angefragte Stimme gewinnt; sonst folgt sie der Sprache (Piper-Parität zu /chat).
-        voice = payload.voice or piper_voice_for_language(route.tts_provider, route.language)
+        voice = payload.voice or voice_for_route(route.tts_provider, route.language, route.voice_gender)
         orchestrator = build_orchestrator(route)
         output = await resolve_output_endpoint(route)
     except SessionOwnershipError as exc:

app/api/ws.py

@@ -27,6 +27,7 @@ from app.dependencies import (
     build_orchestrator,
     resolve_output_endpoint,
     piper_voice_for_language,
+    voice_for_route,
 )
 from app.store import ANONYMOUS_USER_ID, SessionOwnershipError
 from app.audio.vad import EnergyVAD
@@ -122,7 +123,7 @@ async def _run_turn(
     elif effective_voice is not None:
         voice = effective_voice
     else:
-        voice = piper_voice_for_language(route.tts_provider, route.language)
+        voice = voice_for_route(route.tts_provider, route.language, route.voice_gender)
     stream = bool(options.get("stream"))
     # text_only: Geräte-TTS (Web Speech API) spricht selbst -> kein Server-Audio erzeugen/senden.
     text_only = bool(options.get("text_only"))
@@ -233,15 +234,15 @@ async def _voice_turn(websocket, store, user, session_id, audio, fmt, options):
                 audio, fmt=fmt, language=None
             )
             # Stimme folgt der erkannten Sprache (Fallback: Routensprache).
-            effective_voice = piper_voice_for_language(
-                route.tts_provider, detected_language or route.language
+            effective_voice = voice_for_route(
+                route.tts_provider, detected_language or route.language, route.voice_gender
             )
         else:
             # Fix: konfigurierte Sprache an Whisper → Whisper übersetzt automatisch.
             transcript = await orchestrator.stt.transcribe(audio, fmt=fmt, language=route.language)
             detected_language = None
             # Stimme folgt der konfigurierten Sprache.
-            effective_voice = piper_voice_for_language(route.tts_provider, route.language)
+            effective_voice = voice_for_route(route.tts_provider, route.language, route.voice_gender)
     except Exception as exc:
         await websocket.send_json({"type": "error", "status": 502, "detail": str(exc)})
         return