 |
Photo = Naver |
[Alpha Biz= Reporter Kim Jisun] Naver's conversational AI agent, Clova X, is set to enhance its capabilities with the addition of visual information processing through a service update on the 27th.
On the 20th, Naver unveiled new generative AI-based voice synthesis technology on the Clova official website's tech blog. This update will evolve HyperCLOVA X into a 'multimodal' AI capable of processing text, images, and voice simultaneously.
The newly introduced voice AI technology based on HyperCLOVA X advances beyond existing voice recognition and synthesis models. It leverages the exceptional context understanding and instruction interpretation of large language models (LLMs) to improve language structure, pronunciation accuracy, and emotional expression in conversations.
The upgrade will enhance various voice-related applications, including:
Clova Note: AI voice recording
Clova Care Call: AI welfare calls
Clova Dubbing: AI voice synthesis
These improvements make Clova X's multimodal LLM technology more versatile and user-friendly.
AlphaBIZ Kim Jisun(stockmk2020@alphabiz.co.kr)
