Objective: To determine whether external feedback to promote symmetrical weight distribution during standing and walking would improve gait performance and balance in people with stroke. Design: Randomized, controlled, assessor-blinded trial. Setting: Rehabilitation unit and physical therapy department. Subjects: Thirty-five individuals with stroke (mean (SD) age=53.0 (9.3) years) were randomly assigned to an experimental (n=17) or control group (n=18). Time post stroke was less than six months for most subjects (n=27, 77%). Interventions: Subjects participated in 15 rehabilitation sessions including 30 minutes of gait retraining per session. During gait retraining, the experimental group used an insole shoe wedge and sensors set-up (I-ShoWS) while the control group received a conventional programme. The I-ShoWS set-up consisted of a wedge insole and a footswitch for the non-paretic leg and a pressure sensor on the paretic leg. Outcome measures: Gait speed, step length and single support time asymmetry ratio, balance and amount of load on paretic leg during stance were evaluated twice: one day before and after training. Results: The experimental group demonstrated significant increase in standing and gait symmetry compared with the control group (P<0.05). They demonstrated 3 times greater improvement in gait speed than the control group (P=0.02). Balance improvement was significantly greater for the experimental than for the control group (P<0.05). Conclusion: Gait retraining using the I-ShoWS set-up was more effective in restoration of gait speed, standing and walking symmetry and balance than a conventional treatment programme. These results indicate the benefit of implementing feedback during gait retraining. © The Author(s), 2010.