Methods, apparatus, and computer program products are described for providing oral modification of an ASR lexicon of an ASR engine that include receiving, in the ASR engine from a user through a multimodal application, speech for recognition, where the ASR engine includes an ASR lexicon of words capable of recognition by the ASR engine, and the ASR lexicon does not contain at least one word of the speech for recognition; indicating by the ASR engine through the multimodal application to the user that the ASR lexicon does not contain the word; receiving by the ASR engine from the user through the multimodal application an oral instruction to add the word to the ASR lexicon, where the oral instruction is accompanied by an oral spelling of the word from the user; and executing the instruction by the ASR engine.