Today for AI
HOT RADAR
llmHEAT 10.7°

AI CURATED HOT STORY · 11/13/2026

Tencent Hunyuan Unveils Hy Realtime Voice Model with Tool Calling and Singing

1 reports archived1 independent sourcesupdated 11/13/2026, 16:41:34
Synthesis & Latest Updates
1 Sources Cross-Validated

Tencent Hunyuan released Hy Realtime, a real-time speech model with improved intent understanding, instruction following and anthropomorphic expression, plus new agentic tool-calling and singing capabilities. It is already live in Yuanbao voice calls and Tencent customer service, with a Tencent Cloud API coming soon. Next iterations target full-duplex interaction, long-term personalized memory and front/back-end agent interaction.

LATEST/Tencent Hunyuan released Hy Realtime, a real-time speech model with improved intent understanding, instruction following and anthropomorphic expression, plus new agentic tool-calling and singing capabilities. It is already live in Yuanbao voice calls and Tencent customer service, with a Tencent Cloud API coming soon. Next iterations target full-duplex interaction, long-term personalized memory and front/back-end agent interaction.

Hourly heat curve

4 fully observed hours
Now
10.7
Peak
11.618:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. IT之家 · 智能时代T2·78 pts

    Tencent Hunyuan Unveils Hy Realtime Voice Model with Tool Calling and Singing

    • Hy Realtime better reconstructs intent from vague or self-corrected speech and holds multi-turn instruction following over long dialogues
    • The model decides autonomously whether to search the web, unifying search decisions, tool calls and answer generation
    • Co-designed with Tencent Music's Lingyin AI team, it supports song requests by artist, genre and era and sings the result