This paper presents RoboForge, a unified latent-driven framework for text-guided whole-body humanoid locomotion. The approach bridges natural language and physical robot execution through a retarget-free pipeline that couples motion generation and control bidirectionally. A Physical Plausibility Optimization module serves as the coupling interface, refining teacher-student distillation policies with plausibility-centric rewards to eliminate physical artifacts like floating, skating, and penetration. This work enables humanoid robots to execute natural language-directed motions with improved physical feasibility.