88Z AI, 13 November — Tencent Hunyuan has released Hy Realtime, a real-time voice model that enhances spoken language understanding, instruction following, and emotional expression. It supports tool calls like web search and integrates with Tencent Music for song requests. The model is live in Yuanbao voice calls and Tencent Customer Service, with API access coming soon via Tencent Cloud.
At a glance
- Hy Realtime enhances spoken understanding and emotional expression, supporting tool calls like web search
- Integrates with Tencent Music for multi-criteria song requests; live in Yuanbao and customer service, with API coming soon
The update
Tencent Hunyuan has officially launched Hy Realtime, a new real-time voice model. This model focuses on strengthening understanding in authentic spoken language scenarios, optimizing compliance with multi-turn instructions, and significantly enhancing the richness of emotional expression. In terms of functional expansion, Hy Realtime adds Agentic tool calling capabilities, including web search, allowing for more flexible responses to user needs. Furthermore, through deep collaboration with Tencent Music TME Lingyin, the model supports song requests and singing interactions based on criteria such as artist, genre, language, and year. Currently, Hy Realtime is deployed in Yuanbao voice calls and Tencent Customer Service scenarios, and it will soon be available on Tencent Cloud as an open API for developers and enterprise users.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 腾讯混元Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.