✳perchanceai
SavedSubmit a tool
Back to tools

Audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

FreeLinux · macOS · Windows · PythonPricing checked: Sep 11, 2026
AI Music GeneratorAudio Enhancer
Visit website

Best for

Machine learning researchers, sound engineers, and Python developers building local audio compression, sound effects synthesis, and text-to-music systems.

Things to know

Requires local installation with Python, PyTorch, and dedicated GPU hardware; official model weights are restricted to non-commercial research use under CC-BY-NC 4.0.

OverviewGet startedRelated tools
About this tool

Overview

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

MusicGen

A state-of-the-art controllable text-to-music model.

AudioGen

A state-of-the-art text-to-sound model.

EnCodec

A state-of-the-art high fidelity neural audio codec.

Multi Band Diffusion

An EnCodec compatible decoder using diffusion.

Get started

  1. Open the official website and confirm the service is available in your region.
  2. Check the current plan, usage limits and terms for your intended use.
  3. Try a small task with sample data before committing to a paid plan.

Editorial note

Pricing checked: Sep 11, 2026. Free and open-source library released by Meta FAIR under the MIT license; pre-trained model weights (MusicGen, AudioGen, EnCodec, MAGNeT) are made available under the CC-BY-NC 4.0 research license.

Record updated: Sep 11, 2026

Suggest a correction