A method for directional sound capture. The method includes capturing, using a camera device, a sequence of images of a scene comprising a light source attached to a sound source object, detecting, by a hardware processor based on a pattern of local light change across the sequence of images, the light source in the scene, determining a direction of the sound source object by at least determining a location of the light source in at least one image of the sequence of images, transmitting, to a direction control device coupled to a microphone, a control signal to direct a sensitivity direction of the microphone towards the sound source object, and capturing, using the microphone and in response to directing the sensitivity direction of the microphone towards the sound source object, the sound emitted from the sound source object.