Text-to-Speech (TTS) models serve as the backbone for a wide range of applications, from virtual assistants to audiobooks. MyShell pioneers this field by open-sourcing the best TTS models, OpenVoice and MeloTTS. We believe that open-source TTS models are essential for the future of AI and are committed to building a decentralized ecosystem to support their development.

Yet, the TTS landscape is still in its infancy. In this subnet, we aim to gather the wisdom of the whole open-source community to create the best open-source TTS models.

GitHub

HW requirements:

Validator