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>
74 lines
2.4 KiB
Python
74 lines
2.4 KiB
Python
from io import BytesIO
|
|
|
|
from fastapi import APIRouter, Depends, HTTPException, Query
|
|
from fastapi.responses import StreamingResponse
|
|
|
|
from app.errors import RoutingError
|
|
from app.auth import require_user
|
|
from app.store import User, SessionOwnershipError
|
|
from app.dependencies import (
|
|
resolve_route,
|
|
build_orchestrator,
|
|
resolve_output_endpoint,
|
|
get_store,
|
|
piper_voice_for_language,
|
|
)
|
|
from app.quota import enforce_quota, record_usage, QuotaExceededError
|
|
from app.schemas import SpeakRequest
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
@router.post("/speak")
|
|
async def speak(
|
|
payload: SpeakRequest,
|
|
session_id: str | None = Query(
|
|
default=None,
|
|
description="Optional session id to apply a stored route",
|
|
),
|
|
user: User = Depends(require_user),
|
|
):
|
|
overrides = {
|
|
"output_endpoint": payload.output_endpoint,
|
|
"language": payload.language,
|
|
"tts_provider": payload.tts_provider,
|
|
}
|
|
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)
|
|
orchestrator = build_orchestrator(route)
|
|
output = await resolve_output_endpoint(route)
|
|
except SessionOwnershipError as exc:
|
|
raise HTTPException(status_code=403, detail=str(exc))
|
|
except RoutingError as exc:
|
|
raise HTTPException(status_code=422, detail=str(exc))
|
|
|
|
store = get_store()
|
|
try:
|
|
enforce_quota(user, store)
|
|
except QuotaExceededError as exc:
|
|
raise HTTPException(status_code=429, detail=str(exc))
|
|
|
|
try:
|
|
audio = await orchestrator.speak_only(
|
|
payload.text,
|
|
voice=voice,
|
|
language=route.language,
|
|
output=output,
|
|
)
|
|
record_usage(user, store, len(payload.text))
|
|
|
|
headers = {
|
|
"Content-Language": route.language,
|
|
"X-Audio-Format": "pcm",
|
|
"X-Audio-Sample-Rate": "24000",
|
|
"X-Audio-Channels": "1",
|
|
"X-Audio-Sample-Width": "16",
|
|
"X-Output-Endpoint": route.output_endpoint,
|
|
"X-TTS-Provider": route.tts_provider,
|
|
}
|
|
return StreamingResponse(BytesIO(audio), media_type="audio/pcm", headers=headers)
|
|
|
|
except Exception as exc:
|
|
raise HTTPException(status_code=502, detail=str(exc))
|