Effectively managing risk in the stock market has become crucial due to the introduction of online share trading through the use of the internet and computers. In fact, volatility is playing a pivotal role in evaluating the risks associated with many parts of the stock market, including portfolio risk management, derivative pricing, and hedging approaches. Because of this, predicting the volatility of the stock market has recently attracted the attention of various academics. It is obvious that better prediction of the volatility will help investors gain a competitive advantage in the stock market. This paper presents a novel hybrid model that integrates LSTM, GRUs, and GARCH to achieve better prediction of volatility compared to conventional approaches. For this study, we selected three sectoral indices of the Indian stock market and used our hybrid approach to model their volatility. The hybrid model outperforms the classic paradigm, as evidenced by the comparison of performance metrics.