BrightGu

MediumVC

Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

SingleVC

Any-to-one voice conversion using the data augment strategy: pitch shifted and duration remained.

RLVC

AVCDetection

initial

LoINVC

Robust Feature Decoupling in Voice Conversion by using Locality-Based Instance Normalization

MAE-VC

Voice Conversion Based on Learnable Similarity-Guided Masked Autoencoder

Wav2Lip

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

adaptive_voice_conversion

animegan2-pytorch

PyTorch implementation of AnimeGANv2

arcface-pytorch

ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

DiffVC-Content-Controll

Voice Conversion using Learnable Similarity-Guided Masked Autoencoder

dvector

Speaker embedding (d-vector) trained with GE2E loss

ekho

Chinese text-to-speech engine

FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

FragmentVC

Any-to-any voice conversion by end-to-end extracting and fusing fine-grained voice fragments with attention

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

hifigan

An 16kHz implementation of HiFi-GAN for soft-vc.

Sel-CL

SRD-VC

Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion (Interspeech 2022)

ttslearn

ttslearn: Library for Pythonで学ぶ音声合成 (Text-to-speech with Python)

chatgpt-on-wechat

Wechat robot based on ChatGPT, which using OpenAI api and itchat library. 使用ChatGPT搭建微信聊天机器人，基于GPT3.5/4.0 API实现，支持个人微信、公众号、企业微信部署，能处理文本、语音和图片，访问操作系统和互联网。

diffae

Official implementation of Diffusion Autoencoders

Retrieval-based-Voice-Conversion-WebUI

Voice data <= 10 mins can also be used to train a good VC model!

so-vits-svc

SoftVC VITS Singing Voice Conversion

so-vits-svc-fork

so-vits-svc fork with realtime support, improved interface and more features.

TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)