Knowing the execution time of test cases is important to perform test scheduling, prioritization and progress monitoring. This short paper presents a novel approach for predicting the execution time of test cases based on test specifications and available historical data on previously executed test cases. Our approach works by extracting timing information (measured and maximum execution time) for various steps in manual test cases. This information is then used to estimate the maximum time for test steps that have not previously been executed, but for which textual specifications exist. As part of our approach natural language parsing of the specifications is performed to identify word combinations to check whether existing timing information on various test activities already exists or not. Finally, linear regression is used to predict the actual execution time for test cases. A proof-of-concept use-case at Bombardier transportation serves to evaluate the proposed approach.