Abstract: The present invention relates generally to speech recognition systems as applied to voice and electronic message mailing. More particularly the invention is a system and method for converting speech to a text message suitable for sending as an e-mail message and for viewing on a text display device. After an audio message from a caller is received, a text message file is generated and sent to the intended recipient's e-mail address, which has been stored prior to the receipt of the audio message. If the caller is identified, a caller-specific voice file may be used to facilitate speech recognition for generation of the text message file. Also, if the caller specifies a subject for the message, a specialized vocabulary file may be used to facilitate the generation of the text message file.