Open Source Python AI Music Generators

ACE-Step 1.5 is an advanced open-source foundation model for AI-driven music generation that pushes beyond traditional limitations in speed, musical coherence, and controllability by innovating in architecture and training design. It integrates cutting-edge generative techniques—such as diffusion-based synthesis combined with compressed autoencoders and lightweight transformer elements—to produce high-quality full-length music tracks with rapid inference times, capable of generating a complete song in seconds on modern GPUs while remaining efficient enough to run on consumer-grade hardware with minimal memory requirements. Beyond straightforward text-to-music synthesis, ACE-Step 1.5 enables flexible creative workflows, including tasks like cover generation, editing existing tracks, transforming vocals to background accompaniment, and stylistic personalization using low-rank adaptation from just a few example songs.

Audio generation using diffusion models in PyTorch. The code is based on the audio-diffusion-pytorch repository.

Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch. They are basically using text-conditioned AudioLM, but surprisingly with the embeddings from a text-audio contrastive learned model named MuLan. MuLan is what will be built out in this repository, with AudioLM modified from the other repository to support the music generation needs here.

A fully featured audio diffusion library, for PyTorch. Includes models for unconditional audio generation, text-conditional audio generation, diffusion autoencoding, upsampling, and vocoding. The provided models are waveform-based, however, the U-Net (built using a-unet), DiffusionModel, diffusion method, and diffusion samplers are both generic to any dimension and highly customizable to work on other formats. Note: no pre-trained models are provided here, this library is meant for research purposes.

DiffRhythm is an open-source, diffusion-based model designed to generate full-length songs. Focused on music creation, it combines advanced AI techniques to produce coherent and creative audio compositions. The model utilizes a latent diffusion architecture, making it capable of producing high-quality, long-form music. It can be accessed on Huggingface, where users can interact with a demo or download the model for further use. DiffRhythm offers tools for both training and inference, and its flexibility makes it ideal for AI-based music production and research in music generation.

Melodfy is an application that utilizes the power of artificial intelligence (developed by ByteDance) to seamlessly convert audio recordings of piano playing into playable MIDI files.

Implementation of AudioLM, a Language Modeling Approach to Audio Generation out of Google Research, in Pytorch It also extends the work for conditioning with classifier free guidance with T5. This allows for one to do text-to-audio or TTS, not offered in the paper. Yes, this means VALL-E can be trained from this repository. It is essentially the same. This repository now also contains a MIT licensed version of SoundStream. It is also compatible with EnCodec, however, be aware that it has a more restrictive non-commercial license, if you choose to use it.

AGC (Audiogen Codec) is a convolutional autoencoder based on the DAC architecture, which holds SOTA. We found that training with EMA and adding a perceptual loss term with CLAP features improved performance. These codecs, being low compression, outperform Meta's EnCodec and DAC on general audio as validated from internal blind ELO games. We trained (relatively) very low compression codecs in the pursuit of solving a core issue regarding general music and audio generation, low acoustic quality, and audible artifacts, which hinder industry use for these models. Our hope is to encourage researchers to build hierarchical generative audio models that can efficiently use high sequence length representations without sacrificing semantic abilities.

HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan for high-fidelity Foley (sound effects) audio generation synchronized to video scenes. It is designed to generate audio that matches both visual content and textual semantic cues, for use in video production, film, advertising, games, etc. The model architecture aligns audio, video, and text representations to produce realistic synchronized soundtracks. Produces high-quality 48 kHz audio output suitable for professional use. Hybrid architecture combining multimodal transformer blocks and unimodal refinement blocks. Temporal alignment via frame-level synchronization modules (e.g. Synchformer).