A system for automatically merging multiple time-stamped transcriptions is provided. The system includes a transcription server for receiving a signal having time-stamp information, a splitter, a merging utility, and a text output. A method for automatic merging of multiple time-stamped transcriptions comprises the following steps: transferring a signal having timestamp information encoded therein to a splitter which yields a mixed audio output having resultant corresponding audio channels, transferring the mixed audio output to a transcriber server which thereby yields one or more text outputs, and the text outputs being merged by a merging utility with the timestamps included in the signal thereby providing a single text file.