TalkyTalky

TalkyTalky
TalkyTalky Logo

TalkyTalky is an AI-powered language rehabilitation platform that supports the diagnosis and rehabilitation of communication disordersacross the entire lifespan—from language developmental disorders to cognitive impairments. It is Korea’s first fully remote language rehabilitation platform to integrate: • a voice-based AI system for identifying language disorders, • a Large Multimodal Model (LMM) that automatically generates short- and long-term rehabilitation goals and therapy materials, and • a Retrieval-Augmented Generation (RAG)–based personalized counseling system.

Improved Accessibility to
Language Rehabilitation

Improved Accessibility to Language Rehabilitation

Standardization of
Rehabilitation Quality

Standardization of Rehabilitation Quality

Reduction of Medical Costs

Reduction of Medical Costs

Feature

TalkyTalky is the first AI-based, fully remote language rehabilitation platform in Korea designed for all age groups, enabling a complete end-to- end remote language rehabilitation ecosystem.

AI Voice-Based Language Disorder Identification

By performing five structured speech tasks, TalkyTalky analyzes articulation, prosody, voice quality, and linguistic characteristics. This enables automatic screening of language disorders in both online and offline integrated environments.

Speech & Language Rehabilitation- Specialized Multimodal Generative Model (sLMM)

As a text-and-image multimodal generative AI, it can also automatically create visual training materials. Compared to large-scale public LMMs, the sLMM is a lightweight model—approximately one-tenth the size—ensuring enhanced security and operational efficiency.

RAG-Based Personalized Automated Counseling System

Patient speech analysis results and counseling records can be learned as Q&A pair datasets. Based on this data, the system delivers RAG-based responses that provide personalized counseling feedback aligned with each patient’s progress and treatment history.

End-to-End Remote Language Rehabilitation Ecosystem

TalkyTalky is designed as a three-layer integrated architecture: 1. Speech → Language Disorder Identification (AIVIS-based voice analysis) 2. Disorder Results → Personalized Rehabilitation Goal Generation (sLMM) Rehabilitation Goals & Progress Records → Counseling Response Generation (RAG) Through this integrated structure, TalkyTalky enables a complete remote rehabilitation workflow realizing a fully remote language rehabilitation ecosystem.