# LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models

arXiv: https://arxiv.org/abs/2510.15227 · HTML: https://mlsanity.com/paper/2510.15227/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2025.

## Built on by (most cited first, 3 of 3)

- [LongCat-Flash-Omni Technical Report](https://mlsanity.com/paper/2511.00279/) (2025)
- [Improving X-Codec-2.0 for Multi-Lingual Speech: 25 Hz Latent Rate and 24 kHz Sampling](https://mlsanity.com/paper/2601.20185/) (2026)
- [Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning](https://mlsanity.com/paper/2607.02214/) (2026)

## Abstract (arXiv)

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.