47ba213ae3
Features: - Hybrid semantic + keyword quiz search (pgvector HNSW + PostgreSQL ILIKE) - AWS Bedrock Titan Embed V2 embeddings via LiteLLM proxy (0.71 cosine sim) - Multi-provider TTS: OpenAI, AWS Polly (neural), ElevenLabs, Google Cloud TTS - Unified Settings page (profile, theme, Nextcloud integration, admin shortcuts) - Good morning/afternoon greeting on dashboard - manage.py CLI: reset-password, list-users, reembed - Email verification enforced: register no longer returns JWT for unverified users - Quiz search with debounced input, semantic/keyword/title modes, highlighted snippets - TTS button: loading/playing states, voice selector locked during playback - TTS auto-stops when navigating between questions - Footer added; mobile quiz nav overflow fixed; markdown theme body selector fixed - OpenAI Alloy as default TTS voice; favicon added - SMTP configured via smtp2go; password reset rate limiting (3/hour) - PostgreSQL upgraded to pgvector/pgvector:pg16 Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
65 lines
2.2 KiB
Python
65 lines
2.2 KiB
Python
from fastapi import APIRouter, Depends, HTTPException
|
|
from fastapi.responses import Response
|
|
from pydantic import BaseModel
|
|
from sqlalchemy.orm import Session
|
|
|
|
from app.config import settings
|
|
from app.database import get_db
|
|
from app.models.user import User
|
|
from app.models.ai_model_config import AIModelConfig
|
|
from app.services import ai_service
|
|
from app.utils.auth import get_current_user
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
class TTSRequest(BaseModel):
|
|
text: str
|
|
voice: str | None = None # model_id override
|
|
|
|
|
|
@router.get("/voices")
|
|
def get_voices(
|
|
db: Session = Depends(get_db),
|
|
current_user: User = Depends(get_current_user),
|
|
):
|
|
"""Return available TTS voices from DB + env fallback."""
|
|
db_models = db.query(AIModelConfig).filter(
|
|
AIModelConfig.task == "tts",
|
|
AIModelConfig.is_active == True,
|
|
).order_by(AIModelConfig.is_default.desc(), AIModelConfig.name).all()
|
|
|
|
voices = [{"id": m.model_id, "name": m.name, "is_default": m.is_default} for m in db_models]
|
|
return voices
|
|
|
|
|
|
@router.post("/speak")
|
|
def text_to_speech(
|
|
request: TTSRequest,
|
|
db: Session = Depends(get_db),
|
|
current_user: User = Depends(get_current_user),
|
|
):
|
|
"""Convert text to speech using configured or user-selected TTS model."""
|
|
if not request.text.strip():
|
|
raise HTTPException(status_code=400, detail="Text cannot be empty")
|
|
|
|
text = request.text[:2000]
|
|
|
|
if request.voice:
|
|
config = db.query(AIModelConfig).filter(AIModelConfig.model_id == request.voice).first()
|
|
model_id = config.model_id if config else request.voice
|
|
api_key = config.api_key if (config and config.api_key) else None
|
|
else:
|
|
config = db.query(AIModelConfig).filter(
|
|
AIModelConfig.task == "tts",
|
|
AIModelConfig.is_active == True,
|
|
AIModelConfig.is_default == True,
|
|
).first()
|
|
model_id = config.model_id if config else "tts-1:alloy"
|
|
api_key = config.api_key if (config and config.api_key) else None
|
|
|
|
audio = ai_service.generate_tts_audio(text, model_id=model_id, api_key=api_key)
|
|
if audio is None:
|
|
raise HTTPException(status_code=500, detail="TTS generation failed. Check model configuration.")
|
|
|
|
return Response(content=audio, media_type="audio/mpeg")
|