We introduce a multi-modal English-to-Japanese and Japanese-to-English translation system that also translates the speaker's speech motion while synchronizing it to the translated speech. To retain the speaker's facial expression, we substitute only the speech organ's image with the synthesized one, which is made by a three-dimensional wire-frame model that is adaptable to any speaker. Our approach enables image synthesis and translation with an extremely small database. Also, we propose a method to track motion of the face from the video image. In this system, movement and rotation of the head is detected by template matching using a 3D personal face wire-frame model. By this technique, an automatic video translation can be achieved.