LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models
Abstract
This paper presents LongCat-Audio-Codec, an audio tokenizer and detokenizer solution designed for industrial grade end-to-end speech large language models. By leveraging a decoupled model architecture and a multistage training strategy, LongCat-Audio-Codec exhibits robust semantic modeling capabilities, flexible acoustic feature extraction capabilities, and low-latency streaming synthesis capabilities. It encodes speech at an ultra-low frame rate of 16.67 Hz, with a minimum bitrate of 0.43 kbps and a maximum bitrate of 0.87 kbps. Evaluation results demonstrate that LongCat-Audio-Codec achieves strong speech intelligibility and is capable of synthesizing highquality speech at low bitrate, thus effectively balancing coding efficiency and decoding quality. The inference code and model checkpoints of LongCat-Audio-Codec are available at: https://github.com/meituan-longcat/LongCat-Audio-Codec.
Keywords
Cite
@article{arxiv.2510.15227,
title = {LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models},
author = {Xiaohan Zhao and Hongyu Xiang and Shengze Ye and Song Li and Zhengkun Tian and Guanyu Chen and Ke Ding and Guanglu Wan},
journal= {arXiv preprint arXiv:2510.15227},
year = {2025}
}