Kandinsky Lab Open-Sources KVAE-Audio: A High-Fidelity 48kHz Audio Autoencoder

news

Kandinsky Lab (Sber) releases KVAE-Audio, a 166.9M parameter continuous audio autoencoder achieving state-of-the-art reconstruction quality across speech, music, and general sound at 48kHz full bandwidth.

Kandinsky Lab (Sber) has released **KVAE-Audio** (GitHub | HuggingFace), a continuous full-band audio autoencoder that compresses raw waveforms into compact latent representations and reconstructs them with state-of-the-art fidelity.

Overview

KVAE-Audio is a 166.9M parameter continuous audio autoencoder operating at 48 kHz full bandwidth. It compresses raw audio waveforms into a 64-dimensional continuous latent space and reconstructs them with high fidelity across speech, music, and general sound domains. The model is designed as a building block for generative audio pipelines — swapping the autoencoder alone improves generation quality under a fixed generator.

Key Results

KVAE-Audio achieves state-of-the-art or competitive results across multiple domains and metrics:

  • 166.9M parameters — significantly smaller than MMAudio VAE (427.6M), DACVAE MovieGen (107.7M), and SAME-L (852.1M)
  • 64-dim latent space — compact representation ideal for diffusion model integration
  • Outperforms baselines on AudioSet, MUSDB18-HQ, EARS, AudioCaps, Song Describer, and LibriSpeech benchmarks
  • Best overall reconstruction: lowest MEL, STFT, and Waveform distances on AudioSet and MUSDB18-HQ
  • Best generation quality under fixed generator: highest CLAP score (0.344) and FAD scores on AudioCaps

Reconstruction Quality (AudioSet)

ModelParamsLatent DimMEL↓SI-SDR↑SDR↑
MMAudio 44.1kHz VAE427.6M400.636-32.08-2.68
DACVAE MovieGen107.7M1280.6698.389.42
SAME-L (Stable Audio 3 VAE)852.1M2560.9869.5910.35
KVAE-Audio166.9M640.5379.079.92

Generation Quality (AudioCaps)

Under a fixed DiT generator, KVAE-Audio achieves the best CLAP score (0.344), cross-entropy (3.982), and perceptual quality (6.242), outperforming all baselines including the much larger SAME-L.

Architecture

KVAE-Audio is a continuous VAE (not discrete like DAC/EnCodec) designed to produce smooth, information-rich latents suitable for diffusion model training. Key architectural details include:

  • Full-band 48kHz operation — no band-splitting or subband coding
  • Continuous latent space — 64-dim, designed for flow-matching and diffusion backbones
  • Lightweight decoder — efficient enough for real-time applications

Availability

The model is released under the MIT license on HuggingFace with pre-trained weights. The repository includes:

  • Pre-trained VAE encoder and decoder weights
  • Inference scripts
  • Evaluation benchmarks

GitHub: https://github.com/kandinskylab/kvae-audio HuggingFace: https://huggingface.co/kandinskylab/KVAE-Audio

Significance

KVAE-Audio represents an important step for the open-source audio generation ecosystem. Its compact latent space (64-dim vs. 128-256 for competitors) combined with superior reconstruction quality makes it an attractive drop-in replacement for existing audio VAEs in text-to-audio, video-to-audio, and music generation pipelines. The MIT license further lowers the barrier for integration into both research and commercial projects.

Kandinsky Lab Open-Sources KVAE-Audio: A High-Fidelity 48kHz Audio Autoencoder | ComfyUI Wiki