Objective: To examine whether high-intensity home-based respiratory muscle training, that is, with higher loads, delivered more frequently and for longer duration, than previously applied, would increase the strength and endurance of the respiratory muscles, reduce dyspnea and respiratory complications, and improve walking capacity post-stroke. Design: Randomized trial with concealed allocation, blinded participants and assessors, and intention-to-treat analysis. Setting: Community-dwelling patients. Participants: Patients with stroke, who had respiratory muscle weakness (N=38). Interventions: The experimental group received 40-minute high-intensity home-based respiratory muscle training, 7 days per week, for 8 weeks, progressed weekly. The control group received a sham intervention of similar dose. Main Outcome Measures: Primary outcome was inspiratory muscle strength (via maximal inspiratory pressure), whereas secondary outcomes were expiratory muscle strength (maximal expiratory pressure), inspiratory muscle endurance, dyspnea (Medical Research Council score), respiratory complications (hospitalizations), and walking capacity (6-minute walk test). Outcomes were measured at baseline, after intervention, and 1 month beyond intervention. Results: Compared to the control, the experimental group increased inspiratory (27cmH(2)O; 95% confidence interval [95% CI], 15 to 40) and expiratory (42cmH(2)O; 95% CI, 25 to 59) strength, inspiratory endurance (33 breaths; 95% CI, 20 to 47), and reduced dyspnea (-1.3 out of 5.0; 95% CI, -2.1 to -0.6), and the benefits were maintained at 1 month beyond training. There was no significant between-group difference for walking capacity or respiratory complications. Conclusion: High-intensity home-based respiratory muscle training was effective in increasing strength and endurance of the respiratory muscles and reducing dyspnea for people with respiratory muscle weakness post-stroke, and the magnitude of the effect was higher, than that previously reported in studies, which applied standard protocols. (C) 2018 by the American Congress of Rehabilitation Medicine