Text-to-Speech and Voice Synthesis
5 repos
Neural text-to-speech systems and voice cloning models built primarily with PyTorch. This cluster covers open-source TTS engines like MOSS-TTS, ttslibre, and Mars5-TTS, along with related voice synthesis frameworks and implementations. Repositories range from full-featured synthesis systems to specialized models for different languages and voice characteristics, reflecting active development in making high-quality speech generation accessible and customizable.
Jupyter Notebook · 3
Python · 2
tts ·14,387
speech-synthesis ·14,387
pytorch ·13,938
codec ·449
encodec ·449
voicecloning ·449
audio-generation ·449
audio-quantization ·449
speech-to-text ·449
audiobook ·0
