Embodiments of the present disclosure provide a method and a device for processing a video, an electronic device and a storage medium. The method includes the followings. A target recognition is performed to A first video segments and B first speech segments to obtain M second video segments and N second speech segments. A speech processing is performed to the N second speech segments to obtain N target speech text files. First representation information is extracted from the M second video segments to obtain Q pieces of first representation information. A second sound matched with the target character is determined according to the Q pieces of first representation information. The second sound is merged with the N target speech text files to obtain N target speech segments.