SSR-Speech: Towards Stable, Safe and Robust Zero-shot Speech Editing and Synthesis

StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion

An Open-Sourced LLM-empowered Foundation TTS System

vits2 backbone with multilingual-bert

A ggml (C++) re-implementation of tortoise-tts

ChatTTS is a generative speech model for daily dialogue.

Controllable and fast Text-to-Speech for over 7000 languages!

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching

Huawei Grad-TTS for Chinese

Text-to-Speech Latency Benchmark

Awesome speech/audio LLMs, representation learning, and codec models

High fidelity, lightweight, end-to-end, streaming, convolution-based neural audio codec

A generative speech model for daily dialogue.

Inference and training library for high-quality TTS models.

Cross-platform automation framework for all kinds of apps, built on top of the W3C WebDriver protocol

Streaming Text to Speech Web UI

STFT based real-time pitch and timbre shifting in C++ and Python

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

a lightweight voice conversion

Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

Bert-vits2-V2.3 训练和推理

Converts text to speech in realtime

TTS FrontEnd DataSet: Polyphone / Prosody / TextNormalization

C++ version of pyannote audio overlapped speech detection pipeline

ApacheCN 深度学习译文集

Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement

深度定制属于自己的EPG节目预告、高清台标