OpenMOSS / MOSS-Audio-TokenizerView on GitHub
MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, it supports streaming and variable bitrates, delivering SOTA reconstruction and strong performance in generation and understanding—serving as a unified interface for next-generation native audio language models.
166Mar 6, 2026Updated 3 weeks ago

Alternatives and similar repositories for MOSS-Audio-Tokenizer

Users that are interested in MOSS-Audio-Tokenizer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?