AI Transcription API

Production-ready audio transcription service with user authentication and organized file storage.

Setup

1. Install dependencies:

pip install -r requirements.txt

2. Configure environment:

cp .env.example .env
# Edit .env with your credentials

3. Run the API:

python api.py

API Endpoints

• POST /register - Create user account
• POST /login - Get access token
• POST /upload - Upload audio file
• POST /transcribe/{filename} - Process audio file
• GET /files - List user files
• GET /transcriptions - Get transcription history
• GET /download/{filename} - Download results

Usage Example

# Register user
curl -X POST "http://localhost:8000/register" \
  -H "Content-Type: application/json" \
  -d '{"username": "user1", "email": "user@example.com", "password": "password123"}'

# Login
curl -X POST "http://localhost:8000/login" \
  -H "Content-Type: application/json" \
  -d '{"username": "user1", "password": "password123"}'

# Upload file (use token from login)
curl -X POST "http://localhost:8000/upload" \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -F "file=@audio.mp3"

# Transcribe
curl -X POST "http://localhost:8000/transcribe/audio.mp3" \
  -H "Authorization: Bearer YOUR_TOKEN"