Motion planning is one of the main problems studied in the field of robotics. However, it is still challenging for the state-of-the-art methods to handle multiple conditions that allow better paths to be found. For example, considering joint limits, path smoothness and a mixture of Cartesian and joint-space constraints at the same time pose a significant challenge for many of them. This letter proposes to use timed-elastic bands for representing the manipulation motion planning problem, allowing to apply continuously optimized constraints to the problem during the search for a solution. Due to the nature of our method, it is highly extensible with new constraints or optimization objectives. The proposed approach is compared against state-of-the-art methods in various manipulation scenarios. The results show that it is more consistent and less variant, while performing in a comparable manner to that of the state of the art. This behavior allows the proposed method to set a lower-bound performance guarantee for other methods to build upon.