Hy Realtime: Tencent's voice model that talks, calls tools, and sings
Tencent Hunyuan released Hy Realtime on 13 Nov 2026: a real-time speech model that understands spoken instructions, responds in a human-like tone, calls tools directly, and can sing. It is live in Yuanbao voice calls and Tencent customer service, with a Tencent Cloud API to follow.
Why it matters
A real-time voice model with direct tool-calling and singing co-designed with Tencent Music - the first Hunyuan voice model built for live conversation rather than turn-based chat.
What you could build with it
An indie developer could build a voice-first support agent for small online shops that answers calls, looks up orders through tool calls, and hands off to a human only when stuck, charging per resolved call.
Does it hold up?
Too early to judge - it is live in Yuanbao voice calls and Tencent customer service, but there is no public API yet and no independent test of latency or voice quality.
Built with Hy Realtime
- China AI Robotics Semiconductor Telecom Intelligence Briefing 2026-11-14kimkj.com · China AI briefing noting the Hy Realtime release, its Yuanbao deployment and the coming Tencent Cloud API.
- Tencent Hunyuan launches Hy Realtime voice modeliyooo.com · News roundup confirming the 13 Nov launch, tool calling and singing capabilities, and deployment in Yuanbao and customer service.
- Tencent Hunyuan releases Hy Realtime voice modelyicai.com · Original Chinese report of the official Hunyuan announcement on 13 Nov.
Learn more
First spotted on article: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.