OUR AI AGENTS

OUR AI AGENTS

Five Specialized AI Agents Designed to Address Various Tasks in the Educational Sphere.

1. Inclusive Guide. The project aims to support students with visual impairments through the "Inclusive Guide" device, which helps navigate the campus, provides voice instructions, and answers basic questions.

2. AI Avatar. The system automatically generates video lectures featuring a virtual avatar that narrates and presents the material. The AI analyzes the text, detects emotions and intonations, synthesizes speech with synchronized lip movement, and generates gestures and facial expressions. The video is created based on uploaded text and images, and can then be edited by the user. Integration with educational platforms and user feedback helps continuously improve content quality.
3. "E-Curator" Chatbot. The project aims to develop a digital assistant (chatbot) for the university, providing 24/7 access to information, automating responses to frequently asked questions, and reducing staff workload. The chatbot is integrated with the SmartENU system, the enu.kz website, and messengers. It supports personalized responses and adapts based on user experience.

4. SignBridge: AI Assistant for Sign Language Translation. SignBridge is a project aimed at translating text into Kazakh Sign Language using a 3D avatar, making information more accessible to people with hearing impairments. The system includes a gesture recognition module that converts sign language into text in the form of glosses (conventional written representations of signs). By leveraging advanced technologies in computer vision and natural language processing, the startup significantly enhances communication between people with different communication abilities and promotes their social integration.

5. Voice Anti-Spoofing Protection. An intelligent system for detecting fake voices that helps counter threats such as phone fraud, falsified audio recordings, and cybercrime. The service is already deployed on the ML Portal of the University. The system supports online detection, batch processing of audio files, and visual representation in the form of spectral heatmaps highlighting anomalous regions. This makes it valuable for forensic analysis, risk management systems, and educational platforms. Based on artificial intelligence, the system identifies subtle indicators of synthetic speech (TTS, VC) and delivers interpretable results suitable for legal analysis. Special attention is given to privacy: the service does not analyze speech content, operates in a secure environment, and ensures action auditing.

6. Recognition and analysis of runic writing using Optical and Intelligent character recognition. An innovative project designed to preserve and process historical heritage in digital format. The system allows the user to transliterate runic texts into the Latin alphabet, compare them with Egyptian hieroglyphs, process the recognized text, and check it using a reverse program.