A comparative, experimental study with repeated measures has been conducted to evaluate the effect of the use of speech recognition on working postures, productivity and the perception of user friendliness. Fifteen subjects performed a standardised task, first with keyboard and mouse and, after a six week training period, with speech recognition. The use of speech recognition leads to improved postures of wrist, forearm, upper arm and shoulder and improvement of neck movements when compared to the use of keyboard and mouse. Although the observation method was basic, this study provides insight into the potential benefits speech recognition has for posture. However, productivity decreased for most subjects and speech recognition appears to be usable for specific tasks only. From the perspective of productivity and the perception of user friendliness further development of speech recognition software is necessary. Up to now, speech recognition seems especially beneficial for people with WMSD complaints. © 2005 Elsevier Ltd. All rights reserved.