As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/hy-simulmt-30b-a3b/

# Hy-SimulMT-30B-A3B

Tencent, Hunyuan (Hy) family. Status: current. Type: speech and audio. Released: 2026-10-22.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `tencent/Hy-SimulMT-30B-A3B` |  | https://huggingface.co/tencent/Hy-SimulMT-30B-A3B |
| Hugging Face (Interleave variant) | `tencent/Hy-SimulMT-30B-A3B-Interleave` |  | https://huggingface.co/tencent/Hy-SimulMT-30B-A3B-Interleave |
| GitHub (SimulInfer / SimulTrain) |  |  | https://github.com/Tencent-Hunyuan/Hy-SimulMT |

## Pricing

- Price not published.
- Last checked: 2026-10-27

## Specs

- Input: audio
- Output: text, audio
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 1:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- Open simultaneous Chinese–English interpretation: Translates speech while the speaker talks (text plus speech via an external TTS, with voice cloning); vendor-reported StreamLAAL about 3 s on long-form RealSI audio. Source: https://huggingface.co/tencent/Hy-SimulMT-30B-A3B

## Notes

30B MoE with ~3B active; FP8 and GGUF builds published. Speech output needs a configured TTS service. Benchmarks are Tencent's own.

Tencent Hunyuan's open real-time interpreter for meetings and speeches; also inside the Hy Translate app.

Model page: https://postcutoff.com/m/hy-simulmt-30b-a3b/