Résumé : Volatilities, in high-dimensional panels of economic time series with a dynamic factor structure on the levels or returns, typically also admit a dynamic factor decomposition. A two-stage dynamic factor model method recovering common and idiosyncratic volatility shocks therefore was proposed in Barigozzi and Hallin (2016). By exploiting this two-stage factor approach, we build one-step-ahead conditional prediction intervals for large n×T panels of returns. We provide consistency and consistency rates results for the proposed estimators as both n and T tend to infinity. Finally, we apply our methodology to a panel of asset returns belonging to the S&P100 index in order to compute one-step-ahead conditional prediction intervals for the period 2006-2013. A comparison with the componentwise GARCH (1,1) benchmark (which does not take advantage of cross-sectional information) demonstrates the superiority of our approach, which is genuinely multivariate (and high-dimensional), nonparametric, and model-free.