We introduce VoiceCraft, a token infilling neural codec language model, that achieves state-of-the-art performance on both speech editing and zero-shot text-to-speech (TTS) on audiobooks, internet videos, and podcasts. VoiceCraft employs a Transformer decoder architecture and introduces a token rearrangement procedure that combines causal masking and delayed stacking to enable generation within an existing sequence. On speech editing tasks, VoiceCraft produces edited speech that is nearly indistinguishable from unedited recordings in terms of naturalness, as evaluated by humans; for zero-shot TTS, our model outperforms prior SotA models including VALLE and the popular commercial model XTTS-v2. Crucially, the models are evaluated on challenging and realistic datasets, that consist of diverse accents, speaking styles, recording conditions, and background noise and music, and our model performs consistently well compared to other models and real recordings. In particular, for speech editing evaluation, we introduce a high quality, challenging, and realistic dataset named RealEdit. We encourage readers to listen to the demos at https://jasonppy.github.io/VoiceCraft_web.

翻译：我们提出VoiceCraft，一种令牌填充型神经编解码器语言模型，在语音编辑和零样本文本转语音（TTS）任务上，针对有声书、网络视频和播客数据均实现了最先进的性能。VoiceCraft采用Transformer解码器架构，并提出一种令牌重排流程，该流程结合因果掩码和延迟堆叠技术，从而能够在既有序列内进行生成。在语音编辑任务上，经人类评估，VoiceCraft生成的编辑语音在自然度方面与未编辑录音几乎无法区分；在零样本TTS方面，我们的模型超越了包括VALLE和知名商业模型XTTS-v2在内的先前最先进模型。关键在于，模型在包含不同口音、说话风格、录音条件以及背景噪音与音乐等多样挑战性真实数据集上进行了评估，且与其他模型及真实录音相比，我们的模型表现持续优异。特别地，针对语音编辑评估，我们引入了一个高质量、具挑战性且真实的数据集RealEdit。我们鼓励读者访问https://jasonppy.github.io/VoiceCraft_web 收听演示。