Large-scale generative models such as GPT and DALL-E have revolutionized the research community. These models not only generate high fidelity outputs, but are also generalists which can solve tasks not explicitly taught. In contrast, speech generative models are still primitive in terms of scale and task generalization. In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale. Voicebox is a non-autoregressive flow-matching model trained to infill speech, given audio context and text, trained on over 50K hours of speech that are not filtered or enhanced. Similar to GPT, Voicebox can perform many different tasks through in-context learning, but is more flexible as it can also condition on future context. Voicebox can be used for mono or cross-lingual zero-shot text-to-speech synthesis, noise removal, content editing, style conversion, and diverse sample generation. In particular, Voicebox outperforms the state-of-the-art zero-shot TTS model VALL-E on both intelligibility (5.9% vs 1.9% word error rates) and audio similarity (0.580 vs 0.681) while being up to 20 times faster. Audio samples can be found in \url{https://voicebox.metademolab.com}.

翻译：大型生成模型（如GPT和DALL-E）已彻底改变了研究领域。这些模型不仅生成高保真输出，还能成为解决未明确训练任务的通才。相比之下，语音生成模型在规模和任务泛化方面仍显原始。本文提出Voicebox，一种规模最大的多功能文本引导语音生成模型。Voicebox是一种非自回归流匹配模型，通过给定音频上下文和文本训练语音填充任务，其训练数据来自未经过滤或增强的5万小时以上语音。与GPT类似，Voicebox可通过上下文学习执行多种任务，但更具灵活性，因为它还能以未来上下文为条件。Voicebox可用于单语或跨语言零样本文本转语音合成、噪声去除、内容编辑、风格转换及多样化样本生成。特别地，Voicebox在可理解性（词错误率1.9%对5.9%）和音频相似度（0.681对0.580）上均超越最先进的零样本TTS模型VALL-E，同时速度提升高达20倍。音频样本见\url{https://voicebox.metademolab.com}。