---
id: "2026-10-27-tencent-hy-simulmt-open-simultaneous-interpretation"
url: "https://postcutoff.com/e/2026-10-27-tencent-hy-simulmt-open-simultaneous-interpretation/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-10-27"
date_precision: day
category: open-source
importance: 2
confidence: high
status: [Confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-10-27"
---

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/e/2026-10-27-tencent-hy-simulmt-open-simultaneous-interpretation/

# Tencent open-sources Hy-SimulMT, a 30B-A3B Chinese–English simultaneous speech interpreter with about 3 s lag

Tencent Hunyuan released Hy-SimulMT under Apache-2.0: a 30B-parameter mixture-of-experts model (3B active) that translates Chinese and English speech while the speaker is still talking, outputting text and (via a TTS service, with voice cloning) speech. Tencent reports a StreamLAAL latency of about 3 seconds on its long-form RealSI evaluation, the lowest in its comparison, with translation quality above the open models and four of five commercial APIs it tested. Weights went up on Hugging Face on Oct 22; press coverage followed on Oct 27.

## Key facts
- Weights: tencent/Hy-SimulMT-30B-A3B plus an 'Interleave' variant, FP8 and GGUF builds (Hugging Face repos created Oct 22, 2026; licence apache-2.0)
- Function (model card): bidirectional Chinese–English speech-to-speech simultaneous translation; continuous audio input, translated text and speech output; speech output and voice cloning need a configured TTS service
- Tencent's numbers (model card): StreamLAAL ~3 s on RealSI long-form audio, lowest among systems shown; GEMBA quality above compared open models and four of five commercial APIs (vendor evaluation, not independent)
- Tooling: GitHub Tencent-Hunyuan/Hy-SimulMT with the SimulInfer inference service and SimulTrain training tools; also in Tencent's Hy Translate app

## What happened

Open simultaneous interpretation has lagged closed systems (ByteDance's Seed LiveInterpret, OpenAI's and Google's live translation).
Hy-SimulMT is a small-active-parameter open model aimed at meetings and speeches, with inference and training code released.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 180 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 119 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 210 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 149 days after its cutoff

## Sources

1. [Hugging Face: tencent/Hy-SimulMT-30B-A3B (model card)](https://huggingface.co/tencent/Hy-SimulMT-30B-A3B) (huggingface.co, official)
2. [GitHub: Tencent-Hunyuan/Hy-SimulMT](https://github.com/Tencent-Hunyuan/Hy-SimulMT) (github.com, code)
3. [Pandaily: Tencent Hunyuan open-sources Hy-SimulMT](https://pandaily.com/tencent-hunyuan-hy-simulmt-open-source-simultaneous-interpretation-voice-cloning-streamlaal) (pandaily.com, press)
4. [TechNode: Tencent open-sources AI model for real-time Chinese-English interpretation](https://technode.com/2026/10/27/tencent-open-sources-ai-model-for-real-time-chinese-english-interpretation/) (technode.com, press)

## Changes

- 2026-10-27 (filed): Created (model card read directly)

## Related

- 2025-07-24: [ByteDance's LiveInterpret 2.0 interprets Chinese-English simultaneously in your own voice](https://postcutoff.com/e/2025-07-24-bytedance-seed-liveinterpret-2/index.md)
- Models: [Hy-SimulMT-30B-A3B](https://postcutoff.com/m/hy-simulmt-30b-a3b/) (`hy-simulmt-30b-a3b`)