Alibaba unveiled main upgrades to its Tongyi Bailing voice mannequin lineup on December 23, 2025.
The discharge contains Speech Recognition (Enjoyable-ASR), Textual content-to-Speech (Enjoyable-CosyVoice3), and Finish-to-Finish Voice Interplay (Enjoyable-Audio-Chat) fashions, with light-weight variations totally open-sourced.
Enjoyable-ASR helps 31-language blended speech recognition and introduces a RAG mechanism. Enjoyable-CosyVoice3 permits cross-lingual voice cloning. The open-sourced small-parameter fashions make high-performance speech AI possible for on-device deployment.
Supply：GEEKPARK
Elevate your perspective with NextTech Information, the place innovation meets perception.
Uncover the most recent breakthroughs, get unique updates, and join with a world community of future-focused thinkers.
Unlock tomorrow’s traits right now: learn extra, subscribe to our e-newsletter, and change into a part of the NextTech neighborhood at NextTech-news.com
