# AudioCodex: Streaming Autoencoders for Live Audio

**Authors:** Marco Pasini, Javier Nistal, Cyran Aouameur, Stefan Lattner, George Fazekas  
**Published:** 9 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.12375) · [PDF](https://arxiv.org/pdf/2611.12375) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.12375.html)

## Abstract

We introduce AudioCodex, a fully causal autoencoder for live generative audio applications that compresses stereo audio into compact continuous latent sequences at ~10 Hz. It combines a Mean Flow magnitude autoencoder with latent hypersphere projection, bounded-noise augmentation, representation alignment, and adversarial phase recovery to learn representations that support both efficient downstream generation and high-quality reconstruction. Through extensive ablations, we show that AudioCodex outperforms the state-of-the-art in terms of generation-reconstruction trade-off, whilst remaining strictly causal in both encoding and decoding. This work paves the way towards truly real-time interactive and streaming generative audio applications.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.