- Updated OpenAI package from 1.3.7 to 1.51.0 for latest API compatibility
- Added PyTorch and torchaudio dependencies for Whisper model support
- Fixed OpenAI API calls to use new AsyncOpenAI client format
- Updated transcription service to use client.audio.transcriptions.create()
- Updated translation service to use client.chat.completions.create()
- Added proper logging to language detection service
- Added environment variable loading with python-dotenv in main.py
- Fixed import order to comply with linting standards
🤖 Generated with BackendIM
Co-Authored-By: Claude <noreply@anthropic.com>
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
