Multipath transport provides higher usable band-width for a session. It has also been shown to provide load balancing and error resilience for end-to-end multimedia sessions. Two key issues in the use of multiple paths are (1) how to minimize the end-to-end delay, which now includes the delay along the paths and the resequencing delay at the receiver, and (2) how to select paths. In this paper, we present an analytical framework for the optimal partitioning of realtime multimedia traffic that minimizes the total end-to-end delay. Specifically, we formulate optimal traffic partitioning as a constrained optimization problem using deterministic network calculus, and derive its closed form solution. Compared with previous work, our scheme is simpler to implement and enforce. This analysis also greatly simplifies the solution to the path selection problem as compared to previous efforts. Analytical results show that for a given flow and a set of paths, we can choose a minimal subset to achieve the minimum end-to-end delay with O(N) time, where N is the number of available paths. The selected path set is optimal in the sense that adding any rejected path to the set will only increase the end-to-end delay.