878bf785dd
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>
99 lines
3.8 KiB
Python
99 lines
3.8 KiB
Python
import base64
|
|
|
|
import httpx
|
|
|
|
from app.providers.stt.base import STTProvider
|
|
|
|
|
|
class OpenRouterSTTProvider(STTProvider):
|
|
def __init__(self, api_key: str, model: str):
|
|
self.api_key = (api_key or "").strip()
|
|
self.model = (model or "").strip()
|
|
|
|
async def transcribe(self, audio_bytes: bytes, fmt: str, language: str | None = None) -> str:
|
|
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")
|
|
|
|
# OpenRouter /audio/transcriptions erwartet JSON mit base64-Audio
|
|
# (NICHT multipart/form-data). Quelle: OpenRouter-Doku (STT).
|
|
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", "")
|
|
|
|
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")
|