Systems and methods for generating a synthetic video based on an audio are provided. An exemplary system may include a memory storing computer-readable instructions and at least one processor. The processor may execute the computer-readable instructions to perform operations. The operations may include receiving a reference video including a motion picture of a human face and receiving the audio including a speech. The operations may also include generating a synthetic motion picture of the human face based on the reference video and the audio. The synthetic motion picture of the human face may include a motion of a mouth of the human face presenting the speech. The motion of the mouth may match a content of the speech. The operations may further include generating the synthetic video based on the synthetic motion picture of the human face.