TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
This addresses the problem of efficient and high-quality text-to-audio generation for applications requiring fast audio synthesis, though it is incremental in improving alignment methods.
The paper tackles the challenge of aligning text-to-audio models by proposing CLAP-Ranked Preference Optimization (CRPO), a framework for generating and optimizing preference data, resulting in TangoFlux achieving state-of-the-art performance with 515M parameters generating 30 seconds of 44.1kHz audio in 3.7 seconds.
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.