Systems and methods for providing and using translation-enabled multiparty communication sessions

A system for providing a translation-enabled, multiparty communications session, comprising:

• means for receiving a plurality of requests to join a translation-enabled, multiparty communications session from a corresponding plurality of communication session participants;
• means for receiving an audio stream from each of the communication session participants;
• means for mixing the received audio streams from the communication session participants to create a mixed audio stream;
• means for providing the mixed audio stream to the communication session participants;
• means for generating a participant text stream for each participant by converting the audio stream received from each participant into a participant text stream in a first language using computer automated speech-to-text techniques;
• means for creating at least one translated participant text stream for each participant by translating each participant's text stream into a text stream in a second language;
• and
• means for publishing the translated participant text streams.

A system for providing a translation-enabled, multiparty communications session, comprising:

• a communication session application programming interface (API) that is configured to receive a plurality of requests to join a translation-enabled, multiparty communications session from a corresponding plurality of communication session participants and that is configured to receive an audio stream from each of the communication session participants;
• a media bridge that is configured to mix the received audio streams from the communication session participants to create a mixed audio stream and that enables the communication session API to provide the mixed audio stream to the communication session participants;
• a translation service that generates a participant text stream for each participant by converting the audio stream received from each participant into a participant text stream in a first language using computer automated speech-to-text techniques and that creates at least one translated participant text stream for each participant by translating each participant's text stream into a text stream in a second language;
• and
• a translated text API that publishing the translated participant text streams.