skinny.

Latest / Kana & Mari's SoundRepos (English)

sidharthrajaram/StyleTTS2 | voice cloning text to speech engine | GitHub

A Python inference package for StyleTTS2, a neural text-to-speech system designed for highly natural speech synthesis. It supports text-to-speech generation, zero-shot voice cloning from reference WAV files, configurable style and prosody controls, direct style vectors, and automatic model downloading and caching. Related: sidharthrajaram/StyleTTS2 / voice cloning text to speech engine / GitHub

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.