92e4d992b2
Features: - JWT authentication with user registration and login - Video upload to Amazon S3 with file validation (200MB limit) - Audio transcription using OpenAI Whisper API - Text translation using GPT-4 API - Voice cloning and audio synthesis using ElevenLabs API - Video processing with ffmpeg for audio replacement - Complete SQLite database with proper models and migrations - Background task processing for long-running operations - Health endpoint and comprehensive API documentation Tech stack: - FastAPI with SQLAlchemy ORM - SQLite database with Alembic migrations - Amazon S3 for file storage - OpenAI APIs for transcription and translation - ElevenLabs API for voice cloning - ffmpeg for video processing - JWT authentication with bcrypt password hashing
140 lines
4.0 KiB
Python
140 lines
4.0 KiB
Python
from fastapi import APIRouter, Depends, HTTPException, status, BackgroundTasks
|
|
from sqlalchemy.orm import Session
|
|
from pydantic import BaseModel
|
|
from app.db.session import get_db
|
|
from app.models.user import User
|
|
from app.models.video import Video
|
|
from app.models.transcription import Transcription
|
|
from app.utils.auth import get_current_user
|
|
from app.services.transcription_service import transcribe_video_audio
|
|
|
|
router = APIRouter()
|
|
|
|
|
|
class TranscriptionResponse(BaseModel):
|
|
id: int
|
|
video_id: int
|
|
text: str
|
|
created_at: str
|
|
|
|
class Config:
|
|
orm_mode = True
|
|
|
|
|
|
class TranscriptionStartResponse(BaseModel):
|
|
message: str
|
|
video_id: int
|
|
|
|
|
|
async def background_transcribe(video_id: int, video_s3_url: str, db: Session):
|
|
try:
|
|
# Update video status
|
|
video = db.query(Video).filter(Video.id == video_id).first()
|
|
if video:
|
|
video.status = "transcribing"
|
|
db.commit()
|
|
|
|
# Transcribe the video
|
|
transcript_text = await transcribe_video_audio(video_s3_url)
|
|
|
|
if transcript_text:
|
|
# Save transcription to database
|
|
transcription = Transcription(
|
|
video_id=video_id,
|
|
text=transcript_text
|
|
)
|
|
db.add(transcription)
|
|
|
|
# Update video status
|
|
if video:
|
|
video.status = "transcribed"
|
|
|
|
db.commit()
|
|
else:
|
|
# Update video status to error
|
|
if video:
|
|
video.status = "transcription_failed"
|
|
db.commit()
|
|
|
|
except Exception:
|
|
# Update video status to error
|
|
video = db.query(Video).filter(Video.id == video_id).first()
|
|
if video:
|
|
video.status = "transcription_failed"
|
|
db.commit()
|
|
|
|
|
|
@router.post("/{video_id}", response_model=TranscriptionStartResponse)
|
|
async def start_transcription(
|
|
video_id: int,
|
|
background_tasks: BackgroundTasks,
|
|
current_user: User = Depends(get_current_user),
|
|
db: Session = Depends(get_db)
|
|
):
|
|
# Check if video exists and belongs to user
|
|
video = db.query(Video).filter(
|
|
Video.id == video_id,
|
|
Video.user_id == current_user.id
|
|
).first()
|
|
|
|
if not video:
|
|
raise HTTPException(
|
|
status_code=status.HTTP_404_NOT_FOUND,
|
|
detail="Video not found"
|
|
)
|
|
|
|
# Check if transcription already exists
|
|
existing_transcription = db.query(Transcription).filter(
|
|
Transcription.video_id == video_id
|
|
).first()
|
|
|
|
if existing_transcription:
|
|
raise HTTPException(
|
|
status_code=status.HTTP_400_BAD_REQUEST,
|
|
detail="Transcription already exists for this video"
|
|
)
|
|
|
|
# Start background transcription
|
|
background_tasks.add_task(background_transcribe, video_id, video.original_s3_url, db)
|
|
|
|
return TranscriptionStartResponse(
|
|
message="Transcription started in background",
|
|
video_id=video_id
|
|
)
|
|
|
|
|
|
@router.get("/{video_id}", response_model=TranscriptionResponse)
|
|
async def get_transcription(
|
|
video_id: int,
|
|
current_user: User = Depends(get_current_user),
|
|
db: Session = Depends(get_db)
|
|
):
|
|
# Check if video exists and belongs to user
|
|
video = db.query(Video).filter(
|
|
Video.id == video_id,
|
|
Video.user_id == current_user.id
|
|
).first()
|
|
|
|
if not video:
|
|
raise HTTPException(
|
|
status_code=status.HTTP_404_NOT_FOUND,
|
|
detail="Video not found"
|
|
)
|
|
|
|
# Get transcription
|
|
transcription = db.query(Transcription).filter(
|
|
Transcription.video_id == video_id
|
|
).first()
|
|
|
|
if not transcription:
|
|
raise HTTPException(
|
|
status_code=status.HTTP_404_NOT_FOUND,
|
|
detail="Transcription not found"
|
|
)
|
|
|
|
return TranscriptionResponse(
|
|
id=transcription.id,
|
|
video_id=transcription.video_id,
|
|
text=transcription.text,
|
|
created_at=str(transcription.created_at)
|
|
) |