Frequent epileptic seizures result in memory impairment, damage to human brain and so on. Medical experts generally use Electroencephalography (EEG) to diagnose the epilepsy. Visually detecting epileptiform abnormalities is time-consuming and prone to error. The purpose of this work is to help clinicians by providing them computer aided detection system to detect epileptic seizures. Epileptic seizures are usually diagnosed by identifying the sharp spikes in the electroencephalography (EEG) signal. Deep learning-based automated systems techniques have shown appreciable performance in the area of neurological disease detection. In this paper, the authors presented a model having layers of 1D-Convolutional Neural Network (CNN) and long short-term memory (LSTM) for epileptic seizures detection. The authors have obtained a maximum detection rate of 100% between seizure and non-seizure EEG signals using CNN- LSTM network only in 20 epochs. The robustness of the proposed model, has been checked by adding noise to the EEG waveforms. The proposed methodology will be beneficial for neurologists for real-time seizure detection.