Audiobox: Unified Audio Generation with Natural Language Prompts

TL;DR

Audiobox is a versatile, flow-matching based model that enables controllable, multi-modal audio generation from natural language prompts, achieving state-of-the-art results and supporting novel style synthesis.

Contribution

The paper introduces Audiobox, a unified audio generation model that combines description and example prompts, and incorporates self-supervised pretraining and faster solvers for improved performance and controllability.

Findings

Sets new benchmarks on speech and sound generation tasks.

Achieves over 25x faster generation with Bespoke Solvers.

Enables controllable synthesis of diverse audio styles.

Abstract

Audio is an essential part of our life, but creating it often requires expertise and is time-consuming. Research communities have made great progress over the past year advancing the performance of large scale audio generative models for a single modality (speech, sound, or music) through adopting more powerful generative models and scaling data. However, these models lack controllability in several aspects: speech generation models cannot synthesize novel styles based on text description and are limited on domain coverage such as outdoor environments; sound generation models only provide coarse-grained control based on descriptions like "a person speaking" and would only generate mumbling human voices. This paper presents Audiobox, a unified model based on flow-matching that is capable of generating various audio modalities. We design description-based and example-based prompting to enhance controllability and unify speech and sound generation paradigms. We allow transcript, vocal, and other audio styles to be controlled independently when generating speech. To improve model generalization with limited labels, we adapt a self-supervised infilling objective to pre-train on large quantities of unlabeled audio. Audiobox sets new benchmarks on speech and sound generation (0.745 similarity on Librispeech for zero-shot TTS; 0.77 FAD on AudioCaps for text-to-sound) and unlocks new methods for generating audio with novel vocal and acoustic styles. We further integrate Bespoke Solvers, which speeds up generation by over 25 times compared to the default ODE solver for flow-matching, without loss of performance on several tasks. Our demo is available at https://audiobox.metademolab.com/