A conference loudspeaker box, a conference recording method, device and system, and a computer storage medium. The conference recording method comprises: receiving conference audio data duplicated by a conference loudspeaker box (S201); sending the conference audio data to a voice-to-text server for text transformation (S202); and receiving the text from the voice-to-text server (S203). The conference loudspeaker box, the conference recording method, device and system, and the computer storage medium make it convenient to achieve text transformation from a conference voice, achieve the automatic conference recording, improve the work efficiency, and reduce the waste of resources.
展开▼