Biologically inspired control approaches based on central pattern generators (CPGs) with neural oscillators have been drawing much attention to generate rhythmic motion for biped robots that resemble human-like locomotion. This paper describes the design of a neural oscillator based gait rhythm generator using a network of Matsuoka oscillators to generate a walk pattern for biped robots. This includes proper consideration of oscillator's parameters, such as a time constant adaptation rate, coupling factors for mutual inhibitory connections, etc., to obtain a stable and desirable response from the network. The paper examines the characteristics of a CPG network with six oscillators and the effect of assigning symmetrical and asymmetrical coupling coefficients among oscillators within the network structure under different possibilities of inhibitions and excitations. The kinematics and dynamic of a five-link biped robot has been modeled and its joints are actuated through simulation by the torques output from the neural rhythm generator to generate the trajectories for hip, knee, and ankle joints. The parameters of the neural oscillators are tuned to achieve flexible trajectories. The CPG based control strategy are implemented and tested through simulation.