Initial commit: Voice Assistant Gateway mit Konfig-/Routing-Fundament

- FastAPI-Gateway mit REST-Endpunkten (chat/speak/transcribe/devices/sessions/config)
- Geschichtete Konfiguration mit Profilen (local-dev/hybrid/cloud) via TOML + ENV
- Registry-Pattern + einheitliche Route-Aufloesung (Default->Profil->ENV->Session->Request)
- Device Router (strikt, Singleton) und Output-Lifecycle im Orchestrator
- OpenRouter-Adapter (STT multipart/LLM/TTS) + lokale Provider-Stubs
- Regelbasierte Pipeline (Cleaner/Spoken-Adapter/TTS-Normalizer)
- 22 automatisierte Tests; Doku: README, BEDIENUNGSANLEITUNG, Architektur
- Secrets ausschliesslich ueber Umgebung; .env und lokale config gitignored

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

app/providers/tts/base.py

@@ -0,0 +1,5 @@
+from abc import ABC, abstractmethod
+
+class TTSProvider(ABC):
+    @abstractmethod
+    async def synthesize(self, text: str, voice: str | None = None, audio_format: str = "pcm") -> bytes: ...

app/providers/tts/chatterbox.py

@@ -0,0 +1,5 @@
+from app.providers.tts.base import TTSProvider
+
+class ChatterboxTTSProvider(TTSProvider):
+    async def synthesize(self, text: str, voice: str | None = None, audio_format: str = "pcm") -> bytes:
+        return b""

app/providers/tts/openrouter.py

@@ -0,0 +1,62 @@
+import httpx
+
+from app.providers.tts.base import TTSProvider
+
+
+class OpenRouterTTSProvider(TTSProvider):
+    def __init__(self, api_key: str, model: str, voice: str):
+        self.api_key = (api_key or "").strip()
+        self.model = (model or "").strip()
+        self.voice = (voice or "").strip()
+
+    async def synthesize(
+        self,
+        text: str,
+        voice: str | None = None,
+        audio_format: str = "pcm",
+    ) -> bytes:
+        if not self.api_key:
+            raise ValueError("OPENROUTER_API_KEY is empty")
+        if not self.model:
+            raise ValueError("OPENROUTER_TTS_MODEL is empty")
+        if not text or not text.strip():
+            raise ValueError("TTS input text is empty")
+
+        effective_voice = (voice or self.voice).strip()
+        if not effective_voice:
+            raise ValueError("TTS voice is required for OpenRouter TTS")
+
+        payload = {
+            "model": self.model,
+            "input": text.strip(),
+            "voice": effective_voice,
+            "response_format": audio_format,
+        }
+
+        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/speech",
+                    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 TTS error {exc.response.status_code}: {exc.response.text}"
+                ) from exc
+            except httpx.TimeoutException as exc:
+                raise RuntimeError("OpenRouter TTS timeout") from exc
+            except httpx.HTTPError as exc:
+                raise RuntimeError(f"OpenRouter TTS transport error: {exc}") from exc
+
+        if not response.content:
+            raise RuntimeError("OpenRouter TTS returned empty audio content")
+
+        return response.content
+

app/providers/tts/piper.py

@@ -0,0 +1,5 @@
+from app.providers.tts.base import TTSProvider
+
+class PiperTTSProvider(TTSProvider):
+    async def synthesize(self, text: str, voice: str | None = None, audio_format: str = "pcm") -> bytes:
+        return b""