摘要:
A method and device for realizing a voice message visualization service are disclosed. The device at least includes: an information receiving module (401), receiving an original message and a portrait picture sent by a message sender or locally stored, herein, the original message is a text message or a voice message; and a dynamic video generation module (402), extracting facial features from the portrait picture, generating facial expressions, and synthesizing the facial expressions and the original message into dynamic video information, herein, the generated facial expressions correspond to contents of the original message; sending the dynamic video information to a message receiver and displaying the dynamic video information on a terminal of the message receiver. Resources are utilized to a relatively greater extent in the technical scheme, so that a user sends information more conveniently and more interestingly.