WavFlow: Audio Generation in Waveform Space

Hugging Face Daily Papers Papers

Summary

WavFlow generates high-fidelity audio directly in raw waveform space using waveform patchify and amplitude lifting, achieving competitive performance on video-to-audio and text-to-audio benchmarks without intermediate latent representations.

Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-quality video-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmark VGGSound (FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmark AudioCaps (FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative for multimodal audio generation.
Original Article
View Cached Full Text

Cached at: 05/19/26, 10:34 PM

Paper page - WavFlow: Audio Generation in Waveform Space

Source: https://huggingface.co/papers/2605.18749

Abstract

WavFlow generates high-fidelity audio directly in raw waveform space using waveform patchify and amplitude lifting, achieving competitive performance on video-to-audio and text-to-audio benchmarks without intermediate latent representations.

Modern audio generation predominantly relies onlatent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly inraw waveform spacewithout intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids throughwaveform patchifyand introduceamplitude liftingto align signal scales, enabling stable optimization via directx-predictioninflow matching. To capture complex semantic alignment and temporal synchronization, we leverage an automated data pipeline to curate 5 million high-qualityvideo-text-audio triplets, allowing the model to learn fine-grained acoustic patterns from scratch. Experimental results show that WavFlow achieves competitive performance on the video-to-audio benchmarkVGGSound(FD_PaSST: 59.98, IS_PANNs: 17.40, DeSync: 0.44) and the text-to-audio benchmarkAudioCaps(FD_PANNs: 10.63, IS_PANNs: 12.62), matching or exceeding the performance of established latent-based methods. Our work demonstrates that intermediate compression is not a prerequisite for high-quality synthesis, offering a simpler and more scalable alternative formultimodal audio generation.

View arXiv pageView PDFProject pageGitHub16Add to collection

Get this paper in your agent:

hf papers read 2605\.18749

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.18749 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.18749 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.18749 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

WavFlow Generates Audio Directly in Waveform Space (GitHub Repo)

TLDR AI

WavFlow is a new method from Meta AI that generates synchronized, high-fidelity audio from video and text inputs directly in raw waveform space, bypassing latent compression. It achieves performance on par with latent-based methods on VGGSound and AudioCaps benchmarks.