Toucan TTS: An MIT Licensed Text-to-Speech Advanced Toolbox with Speech Synthesis in More Than 7000 Languages

ToucanTTS, developed by the Institute for Natural Language Processing at the University of Stuttgart, is an advanced text-to-speech toolkit capable of synthesizing speech in over 7,000 languages. Built using PyTorch and Python, it supports multi-speaker voice synthesis and human-in-the-loop editing for flexible customization. Featuring advancements like the FastSpeech 2 architecture and PortaSpeech-inspired PostNet, ToucanTTS offers high-quality, natural-sounding speech, particularly benefiting low-resource languages with its unique articulatory phoneme input method.