ChatTTS is a generative speech model for daily dialogue.

Software Automatic Mouth - Tiny Speech Synthesizer

Fast TorToiSe inference (5x or your money back!)

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

持续更新中~Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

VITS for Mandarin. Support Windows and Linux, low-end and high-end hardwares

Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform with Multilingual Cleaners

基于随机森林和条件随机场的中文韵律预测模型

This repository is a collection of TTS Models in TFLite

论文复现，使用pos标记进行中文多音字消歧

Convert your voice to favorite voice

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model

Tacotron2 + LPCNET for complete End-to-End TTS System

Efficient neural speech synthesis

Multi-speaker Tacotron in TensorFlow.

Fatcord's Alternative WaveRNN (Faster training)

DeepMind's Tacotron-2 Tensorflow implementation