Hy-SimulMT-30B-A3B-FP8

Use it to build or run live Chinese–English translation for meetings, speeches, interviews, and other conversations.

Availability

Released; model resources linked from the project

Pricing model

Not established

Deployment

Model resources and inference service provided through the GitHub repository

Privacy

Not established

Licence

Apache-2.0

• Hy-SimulMT supports bidirectional speech-to-speech translation between Chinese and English. ^[1]

  **Hy-SimulMT** is a real-time simultaneous translation model developed by Tencent Hunyuan, supporting **bidirectional speech-to-speech translation between Chinese and English**.

• The model continuously receives incoming audio and translates as the speaker talks, producing translated text and speech. ^[1]

  It continuously receives incoming audio and translates as the speaker talks, producing both translated text and speech.

• Hy-SimulMT supports real-time voice cloning that preserves the speaker's vocal characteristics. ^[1]

  Hy-SimulMT supports real-time voice cloning, preserving the original speaker's vocal characteristics while generating speech in the target language.

• Speech output and voice cloning require a configured TTS service. ^[1]

  Speech output and voice cloning require a configured TTS service.

• Hy-SimulMT was released with project and model resources linked from the release announcement. ^[1]
• In the RealSI long-form audio evaluation, Hy-SimulMT achieved a StreamLAAL of approximately 3 seconds, the lowest among the systems shown. ^[1]

  In our **RealSI long-form audio evaluation**, Hy-SimulMT achieved a **StreamLAAL of approximately 3 seconds**, the lowest among the systems shown in the comparison.

• New models bring live speech translation and voice features Daily brief 2026-10-28