zero-shot voice conversion & singing voice conversion, with real-time support

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audi…

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

AcademiCodec: An Open Source Audio Codec Model for Academic Research

SoftVC VITS Singing Voice Conversion

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

A book about Text-to-Speech (TTS) in Chinese.

A Flow-based Generative Network for Speech Synthesis

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

This github contains the network architectures of NeuralVoicePuppetry.

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN) with Pytorch

Concatenate wavs(for unit selection)

Implementation code of non-parallel sequence-to-sequence VC

End-to-end training of sparse deep neural networks with little-to-no performance loss.

Contains code for our work on speech to singing conversion (ICASSP 2020)

SincNet is a neural architecture for efficiently processing raw audio samples.

Facebook AI Research Automatic Speech Recognition Toolkit

ONNX Runtime

A Pytorch implementation of "FloWaveNet: A Generative Flow for Raw Audio"

A Pytorch Implementation of ClariNet

A Python wrapper for the high-quality vocoder "World"

DeepMind's Tacotron-2 Tensorflow implementation

A high-quality speech analysis, manipulation and synthesis system

Acceleration package for neural networks on multi-core CPUs