# Tencent Releases a 1.5-Billion-Parameter Speech Model Under an MIT License

AuK handles text-to-speech, content and acoustic editing, denoising and source separation through one natural-language instruction interface, with weights on Hugging Face and ModelScope.

- Published: 2026-09-11T06:22:22.078Z
- Canonical: https://polylog.news/ai/2026-09-11/tencent-releases-a-1-5-billion-parameter-speech-model-under
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Tencent Hunyuan on GitHub](https://github.com/Tencent-Hunyuan/AuK), [Hugging Face](https://huggingface.co/tencent/AuK)

Tencent's Hunyuan group, working with a Shanghai university team, released AuK, a 1.5-billion-parameter foundation model for speech generation and editing, with code and weights under an MIT license. A Russian-language AI channel flagged th…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-11/tencent-releases-a-1-5-billion-parameter-speech-model-under (subscription information: https://polylog.news/pricing).