A system and method for assisting communication through predictive speech is provided. A database includes commonly used words, phrases, and images, each associated with at least one context cue. A processor is configured to determine the user's context and provide a number of possible initial phrases associated with the determined context. Further words, phrases, or images are provided following, and based at least in part on, user selection of the initial phrase. The selected initial phrase and the subsequently selected words, phrases, and images are communicated.