feat: Geräte-TTS, native Stimmen, Favicon, Auth-Gate, UI-Fixes

Web-UI / TTS:
- Geräte-TTS ("📱 Gerät"): Antwort wird on-device vorgelesen (Web Speech
  API), Server sendet nur Text (text_only) -> spart Bandbreite/Kosten.
  Mobil-Default, geräte-lokale Speicherung, iOS-Autoplay-Freischaltung.
- Vorlese-Symbol (🔊) je Bubble: Hybrid-Replay (Assistent-PCM gecacht,
  Eingabe via /api/speak); SVG-Icon mit kontrastreicher Farbe.
- Kombiniertes Sprachmenü (Flex + feste Sprachen) statt separatem Modus-Menü.
- "Neues Gespräch"-Button (frische Session gegen Sprach-Trägheit).
- Dark-Mode: lesbare <option>-Popups (Kontrast-Fix).
- Favicon (SVG + PNG-Fallbacks) aus mund.png.

TTS-Backend:
- Sprache wird an alle TTS-Provider durchgereicht; Piper-Stimme folgt der
  Sprache; Chatterbox mehrsprachig + cross-lingual.
- Native Referenz-Stimmen je Sprache (config/voices/<lang>.wav, FLEURS CC-BY),
  loudness-normalisiert.

LLM-Sprache:
- Antwort folgt zuverlässig der gewählten Sprache (verstärkte Anweisung +
  Erinnerung an der letzten Nutzer-Nachricht gegen History-Trägheit).

Admin / Auth:
- Wörterbuch: alle 8 Sprachen, Zeilen editierbar, alphabetische Sortierung.
- Web-UI hinter Auth-Gate (Redirect auf SSO_LOGIN_URL / 401); Favicons offen.
- Log-Tab: Hinweis, wenn der systemd-Dienst nicht aktiv ist.
- Einstellungen: Hinweis "pro Nutzer überschreibbar" bei Sprache/Modus/Qualität.

Doku (BEDIENUNGSANLEITUNG.md): Geräte-TTS §6.5.0, Fix/Flex §6.6, native
Stimmen §6.5.3, llama.cpp<->Ollama-Wechsel §4.7, Auth/SSO §7.4.

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

app/providers/stt/base.py

@@ -1,5 +1,17 @@
 from abc import ABC, abstractmethod
 
+
 class STTProvider(ABC):
     @abstractmethod
     async def transcribe(self, audio_bytes: bytes, fmt: str, language: str | None = None) -> str: ...
+
+    async def transcribe_detect(
+        self, audio_bytes: bytes, fmt: str, language: str | None = None
+    ) -> tuple[str, str | None]:
+        """Transkribiert und liefert (text, detected_language).
+
+        Standardimplementierung delegiert an transcribe(); detected_language=None.
+        Provider mit Spracherkennung überschreiben diese Methode.
+        """
+        text = await self.transcribe(audio_bytes, fmt, language=language)
+        return text, None

app/providers/stt/faster_whisper.py

@@ -38,12 +38,24 @@ class FasterWhisperProvider(STTProvider):
         self.device = device or settings.faster_whisper_device
         self.compute_type = compute_type or settings.faster_whisper_compute_type
 
-    def _transcribe_sync(self, audio_bytes: bytes, language: str | None) -> str:
+    def _transcribe_sync(
+        self, audio_bytes: bytes, language: str | None
+    ) -> tuple[str, str | None]:
         model = _load_model(self.model_size, self.device, self.compute_type)
-        segments, _info = model.transcribe(io.BytesIO(audio_bytes), language=language)
-        return "".join(segment.text for segment in segments).strip()
+        segments, info = model.transcribe(io.BytesIO(audio_bytes), language=language)
+        text = "".join(segment.text for segment in segments).strip()
+        detected = getattr(info, "language", None)
+        return text, detected
 
     async def transcribe(self, audio_bytes: bytes, fmt: str, language: str | None = None) -> str:
+        if not audio_bytes:
+            raise ValueError("STT input audio is empty")
+        text, _ = await asyncio.to_thread(self._transcribe_sync, audio_bytes, language)
+        return text
+
+    async def transcribe_detect(
+        self, audio_bytes: bytes, fmt: str, language: str | None = None
+    ) -> tuple[str, str | None]:
         if not audio_bytes:
             raise ValueError("STT input audio is empty")
         return await asyncio.to_thread(self._transcribe_sync, audio_bytes, language)

app/providers/stt/openrouter.py

@@ -52,4 +52,48 @@ class OpenRouterSTTProvider(STTProvider):
             except httpx.HTTPError as exc:
                 raise RuntimeError(f"OpenRouter STT transport error: {exc}") from exc
 
-        return response.json().get("text", "")
+        data = response.json()
+        return data.get("text", "")
+
+    async def transcribe_detect(
+        self, audio_bytes: bytes, fmt: str, language: str | None = None
+    ) -> tuple[str, str | None]:
+        if not self.api_key:
+            raise ValueError("OPENROUTER_API_KEY is empty")
+        if not self.model:
+            raise ValueError("OPENROUTER_STT_MODEL is empty")
+        if not audio_bytes:
+            raise ValueError("STT input audio is empty")
+
+        payload = {
+            "model": self.model,
+            "input_audio": {
+                "data": base64.b64encode(audio_bytes).decode("utf-8"),
+                "format": fmt,
+            },
+        }
+        if language:
+            payload["language"] = language
+
+        timeout = httpx.Timeout(connect=10.0, read=120.0, write=30.0, pool=10.0)
+        async with httpx.AsyncClient(timeout=timeout) as client:
+            try:
+                response = await client.post(
+                    "https://openrouter.ai/api/v1/audio/transcriptions",
+                    headers={
+                        "Authorization": f"Bearer {self.api_key}",
+                        "Content-Type": "application/json",
+                    },
+                    json=payload,
+                )
+                response.raise_for_status()
+            except httpx.HTTPStatusError as exc:
+                raise RuntimeError(
+                    f"OpenRouter STT error {exc.response.status_code}: {exc.response.text}"
+                ) from exc
+            except httpx.TimeoutException as exc:
+                raise RuntimeError("OpenRouter STT timeout") from exc
+            except httpx.HTTPError as exc:
+                raise RuntimeError(f"OpenRouter STT transport error: {exc}") from exc
+        data = response.json()
+        return data.get("text", ""), data.get("language")