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 audio, music, and speech generation research and development.

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Official PyTorch implementation of BigVGAN (ICLR 2023)

Deep Convolutional Neural Networks for Musical Source Separation

A soundfont editor for quickly designing musical instruments.

openFrameworks addon for audio synthesis and generative music

Pytorch implementation of BigVSAN

Library for pure Rust advanced audio synthesis.

PC Music Generator - a Virtual Modular Synthesizer

A python toolkit for automatic audio/MIDI rendering using REAPER

jazznet dataset of piano patterns for music audio machine learning research

Pythonic audio processing and generation framework

Wavetable creation and manipulation tool

Interactive audio in Jupyter

Benchmarking for Audio-Text and Audio-Visual Generation; Supports FAD, FD_VGG, FD_PANNs, FD_PaSST, IS_PaSST, IS_PANNs, KL_PaSST, KL_PANNs, LAION-CLAP, MS-CLAP, DeSync

A creative coding library.

Text prompt steered synthetic audio generators

Generative voice cloning model using TTS synthesis with state-of-the-art Zero-Shot Multi-Speaker functionality. An web api built with the YourTTS TTS model to clone and generate realistic audio waves

Deep Performer: Score-to-audio music performance synthesis

Really-Real Time FM Tone Transfer Audio Pluigin

Code for our paper "VaPar Synth - A Variational Parametric Model for Audio Synthesis"

Python library for generating ambient music from text descriptions. No GPU required. Turn text into sound with a single line of code.

[CVPR 2025] Pytorch implementation of the paper "Hearing Anywhere in Any Environment"

Code associated with the paper "Physical Modeling using Recurrent Neural Networks with Fast Convolutional Layers"

midio will work really hard to generate you endlessly interesting audio on the fly.

Latent Timbre Synthesis (LTS) is audio synthesis framework using Variational Autoencoders

Pure-python library for generating audio tones, with support for polyphony, pitch-bending and vibrato

A cross-platform modular digital synth written in C++, for real-time sound synthesis and audio experimentation.

A Max/MSP package for sound experimentation and algorithmic composition

IADT Y4 - Final Year Project: A web-based subtractive synthesizer 🥭🎹