Even though natural language voice-only input applications may be quite successful in desktop or office environments, voice may not be an appropriate input modality in some mobile situations. This necessitates the addition of a secondary input modality, ideally one with which users can express the same amount of content as they can with natural language using a similar amount of effort. The work presented here describes one possible solution to this problem - leveraging existing help mechanisms in the voice-only application to support an additional non-voice input modality, in our case text input. The user can choose the speech or text modality according to their current situation (e.g. noisy environment) and have the same interaction experience.