FIELD: communication technology.
SUBSTANCE: invention relates to the field of speech-to-text transcription and the field of communication technology, namely to the speech-to-text transcription in a conference call. For this purpose, speech-to-text transcription requests are sent by at least two terminals, where speech-to-text transcription requests include a first identifier and a second identifier, and allocating a session to at least two terminals, so that in requests for speech-to-text transcription sent by at least two terminals, terminals that have the same first identifier or the same second identifier are allocated the same session. Receive, through the use of a packet-switched domain, a voice stream whose sampling rate is greater than 8 kHz, and which is sent by at least one terminal in one conference call, where the conference call corresponds to one session; convert voice stream to text; and send text to the terminal in the conference call.
EFFECT: technical result is to reduce the time and improve the accuracy of receiving text converted from a voice in a conference call.
16 cl, 8 dwg, 3 tbl
