Tangoflux: Super Fast And Faithful Text To Audio Generation With Flow Matching And Clap-ranked Preference Optimization

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhung2024tangoflux

Related papers

• Text-to-audio Generation Using Instruction-tuned LLM And Latent Diffusion Model (2023)0.00
• Auffusion: Leveraging The Power Of Diffusion And Large Language Models For Text-to-audio Generation (2024)11.19
• Glow-tts: A Generative Flow For Text-to-speech Via Monotonic Alignment Search (2020)0.00
• ETTA: Elucidating The Design Space Of Text-to-audio Models (2024)0.00
• Audiocomposer: Towards Fine-grained Audio Generation With Natural Language Descriptions (2024)5.24
• Flashaudio: Rectified Flows For Fast And High-fidelity Text-to-audio Generation (2024)5.13
• Retrieval-augmented Text-to-audio Generation (2023)0.00
• Consistencytta: Accelerating Diffusion-based Text-to-audio Generation With Consistency Distillation (2023)6.77