Tencent Hunyuan releases Hy Realtime speech model with tool calling and singing capabilities
Original title:实时语音模型 Hy Realtime 发布:能说会唱、还能调用工具
AI summary
Tencent Hunyuan has released Hy Realtime, a new real-time speech model that adds agentic tool calling and singing capabilities on top of core abilities such as speech understanding, instruction following and human-like expression. It is now live in Yuanbao voice calls and Tencent customer service, and will soon be offered as an API service on Tencent Cloud.
Key Takeaways
- Tencent Hunyuan has released Hy Realtime,a new real-time speech model that adds agentic tool…
- instruction following and human-like expression.
- It is now live in Yuanbao voice calls and Tencent customer service,and will soon be offered as an…
Quick Facts
- Published
- Source
- 公众号:腾讯混元
- Category
- Model Releases
- Topic
- AgentModel Releases
- AI score
- 66
官方完整披露了模型在跨模态对齐、数据体系与强化学习上的训练细节,并给出已上线产品和体验入口,便于读者了解其实际能力构成。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Tencent Hunyuan releases Hy Realtime speech model with tool calling and singing capabilities. November 13, 2026. https://new.nat6.net/en/news/qp41q77z9ge5hsyrh9kra0c7k/