Deep learning transformer models become important by training on text data based on self-attention mechanisms. This manuscript demonstrated a novel universal spam detection model using pre-trained Google's Bidirectional Encoder Representations from Transformers (BERT) base uncased models with four datasets by efficiently classifying ham or spam emails in real-time scenarios. Different methods for Enron, Spamassain, Lingspam, and Spamtext message classification datasets, were used to train models individually in which a single model was obtained with acceptable performance on four datasets. The Universal Spam Detection Model (USDM) was trained with four datasets and leveraged hyperparameters from each model. The combined model was finetuned with the same hyperparameters from these four models separately. When each model using its corresponding dataset, an F1-score is at and above 0.9 in individual models. An overall accuracy reached 97%, with an F1 score of 0.96. Research results and implications were discussed.