Tencent's AuK Tops Hugging Face Trending With Cloning, Editing and Separation

tencent · hf · 2026-09-11

Tencent's speech model AuK is trending on Hugging Face under the text-to-speech pipeline.

Its tags indicate a broad capability set: zero-shot voice cloning, speech generation and editing, speech enhancement, plus source separation and speech separation — making it an unusually all-in-one audio model.

Original post →

More from Multimodal

Multimodal channel →