backend/app/core/config.py

"""
VoiceForge Configuration
Pydantic Settings for application configuration
"""

from functools import lru_cache
from typing import List
from pydantic_settings import BaseSettings, SettingsConfigDict
from pydantic import Field


class Settings(BaseSettings):
    """Application settings loaded from environment variables"""
    
    model_config = SettingsConfigDict(
        env_file=".env",
        env_file_encoding="utf-8",
        case_sensitive=False,
        extra="allow",  # Allow extra env vars without error
    )
    
    # Application
    app_name: str = "VoiceForge"
    app_version: str = "1.0.0"
    debug: bool = False
    
    # API Server
    api_host: str = "0.0.0.0"
    api_port: int = 8000
    
    # Database
    database_url: str = Field(
        default="sqlite:///./voiceforge.db",
        description="Database connection URL (SQLite for dev, PostgreSQL for prod)"
    )
    
    # Redis
    redis_url: str = Field(
        default="redis://localhost:6379/0",
        description="Redis connection URL for caching and Celery"
    )
    
    # Google Cloud
    google_application_credentials: str = Field(
        default="./credentials/google-cloud-key.json",
        description="Path to Google Cloud service account JSON key"
    )
    
    # AI Services Configuration
    use_local_services: bool = Field(
        default=True,
        description="Use local free services (Whisper + EdgeTTS) instead of Google Cloud"
    )
    whisper_model: str = Field(
        default="small",
        description="Whisper model size (tiny, base, small, medium, large-v3)"
    )
    
    # Security
    secret_key: str = Field(
        default="your-super-secret-key-change-in-production",
        description="Secret key for JWT encoding"
    )
    access_token_expire_minutes: int = 30
    algorithm: str = "HS256"
    hf_token: str | None = Field(default=None, description="Hugging Face Token for Diarization")
    
    # File Storage
    upload_dir: str = "./uploads"
    max_audio_duration_seconds: int = 600  # 10 minutes
    max_upload_size_mb: int = 50
    
    # Supported Languages
    supported_languages: str = "en-US,en-GB,es-ES,es-MX,fr-FR,de-DE,ja-JP,ko-KR,zh-CN,hi-IN"
    
    # Audio Formats
    supported_audio_formats: str = "wav,mp3,m4a,flac,ogg,webm"
    
    @property
    def supported_languages_list(self) -> List[str]:
        """Get supported languages as a list"""
        return [lang.strip() for lang in self.supported_languages.split(",")]
    
    @property
    def supported_audio_formats_list(self) -> List[str]:
        """Get supported audio formats as a list"""
        return [fmt.strip() for fmt in self.supported_audio_formats.split(",")]


# Language metadata for UI display
LANGUAGE_METADATA = {
    "en-US": {"name": "English (US)", "flag": "🇺🇸", "native": "English"},
    "en-GB": {"name": "English (UK)", "flag": "🇬🇧", "native": "English"},
    "es-ES": {"name": "Spanish (Spain)", "flag": "🇪🇸", "native": "Español"},
    "es-MX": {"name": "Spanish (Mexico)", "flag": "🇲🇽", "native": "Español"},
    "fr-FR": {"name": "French", "flag": "🇫🇷", "native": "Français"},
    "de-DE": {"name": "German", "flag": "🇩🇪", "native": "Deutsch"},
    "ja-JP": {"name": "Japanese", "flag": "🇯🇵", "native": "日本語"},
    "ko-KR": {"name": "Korean", "flag": "🇰🇷", "native": "한국어"},
    "zh-CN": {"name": "Chinese (Mandarin)", "flag": "🇨🇳", "native": "中文"},
    "hi-IN": {"name": "Hindi", "flag": "🇮🇳", "native": "हिन्दी"},
}


@lru_cache
def get_settings() -> Settings:
    """Get cached settings instance"""
    return Settings()