TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

TL;DR

TangoFlux is a fast, high-quality text-to-audio model that uses flow matching and a novel preference optimization method to improve alignment, achieving state-of-the-art results with efficient generation speed.

Contribution

We introduce TangoFlux, a highly efficient TTA model with a new preference optimization framework called CRPO that enhances alignment and performance.

Findings

Generates 30 seconds of audio in 3.7 seconds on a single GPU

CRPO-generated preference dataset outperforms existing datasets

TangoFlux achieves state-of-the-art results in objective and subjective benchmarks

Abstract

We introduce TangoFlux, an efficient Text-to-Audio (TTA) generative model with 515M parameters, capable of generating up to 30 seconds of 44.1kHz audio in just 3.7 seconds on a single A40 GPU. A key challenge in aligning TTA models lies in the difficulty of creating preference pairs, as TTA lacks structured mechanisms like verifiable rewards or gold-standard answers available for Large Language Models (LLMs). To address this, we propose CLAP-Ranked Preference Optimization (CRPO), a novel framework that iteratively generates and optimizes preference data to enhance TTA alignment. We demonstrate that the audio preference dataset generated using CRPO outperforms existing alternatives. With this framework, TangoFlux achieves state-of-the-art performance across both objective and subjective benchmarks. We open source all code and models to support further research in TTA generation.