Real-time bi-directional language translation using dual language models in conference calls

A system for providing real-time language translation in a conference call environment, the system comprising:

• at least one processor;
• and
• at least one memory storage device storing instructions thereon, which, when executed by the at least one processor, cause the system to:
• establish a conference call session between a first participant device and a second participant device;
• initialize a first translator bot and a second translator bot, wherein each translator bot establishes a bidirectional communication connection with a voice service client using configuration data received from a voice server configuration interface, and each translator bot is added as a participant to the conference call session;
• configure the first translator bot with a first ASR model for the first language and first TTS model for the second language, and configure the second translator bot with a second ASR model for the second language and second TTS model for the first language;
• receive, at the voice service client, first audio content from the first participant device in the first language;
• route the first audio content to the first ASR model to generate first text content;
• transmit the first text content via the communication connection to a customer-provided server infrastructure;
• receive first translated text from the customer-provided server infrastructure;
• convert the first translated text to first translated audio using the first TTS model;
• and
• transmit the first translated audio to the second participant device.

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the processor to perform operations comprising:

• establishing a conference call session between a first participant device and a second participant device;
• initializing a first translator bot and a second translator bot, wherein each translator bot establishes a bidirectional communication connection with a voice service client using configuration data received from a configuration interface, and each translator bot is added as a participant to the conference call session;
• configuring the first translator bot with a first automatic speech recognition (ASR) model for a first language and first text-to-speech (TTS) model for the second language, and configuring the second translator bot with a second ASR model for the second language and second TTS model for the first language;
• receiving, at the voice service client, first audio content from the first participant device, the first audio content in the first language;
• routing, by the first translator bot, the first audio content to the first ASR model to generate first text content in the first language;
• transmitting the first text content via the bidirectional communication connection to a customer-provided server infrastructure for translation;
• receiving first translated text from the customer-provided server infrastructure via the bidirectional communication connection;
• converting, via the first TTS model, the first translated text to first translated audio in the second language;
• and
• transmitting the first translated audio to the second participant device through the conference call session.