YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone

YourTTS brings the power of a multilingual approach to the task of zero-shot\nmulti-speaker TTS. Our method builds upon the VITS model and adds several novel\nmodifications for zero-shot multi-speaker and multilingual training. We\nachieved state-of-the-art (SOTA) results in zero-shot multi-speaker TTS and\nresults comparable to SOTA in zero-shot voice conversion on the VCTK dataset.\nAdditionally, our approach achieves promising results in a target language with\na single-speaker dataset, opening possibilities for zero-shot multi-speaker TTS\nand zero-shot voice conversion systems in low-resource languages. Finally, it\nis possible to fine-tune the YourTTS model with less than 1 minute of speech\nand achieve state-of-the-art results in voice similarity and with reasonable\nquality. This is important to allow synthesis for speakers with a very\ndifferent voice or recording characteristics from those seen during training.\n