Tencent Hunyuan Unveils Hy Realtime: A Brand-New Real-Time Speech Model
19 hour ago / Read about 0 minute
Author:小编   

On November 13, Tencent Hunyuan launched Hy Realtime, its brand-new real-time speech model. Hy Realtime delivers outstanding performance in core dialogue capabilities—including speech understanding, instruction following, and human-like expression—while introducing agentic tool calling and singing features. The model is now available in products such as Yuanbao's voice call service and Tencent Customer Service, and will soon be offered on Tencent Cloud as an external API service. Beyond everyday conversation, Hy Realtime can determine whether a web search is needed based on the dialogue context and user intent, seamlessly handling search decisions, tool invocation, and answer generation in a single unified flow.