How much does AudioCraft cost to use?

AudioCraft is completely free and open source. There are no per-call fees or pricing tiers. However, you must self-host the software, meaning you need to provide your own GPU hardware to run the models.

Is AudioCraft suitable for creating finished songs?

No, AudioCraft is a research release, not a polished consumer product. It lacks a hosted web app or managed API. If you want a click-and-go experience for finished songs, use alternatives like Suno, Udio, or ElevenLabs Music.

What models are included in the AudioCraft toolkit?

The toolkit bundles three main models: MusicGen for text-to-music generation, AudioGen for creating environmental sound effects from text prompts, and EnCodec, a neural audio codec that compresses audio into discrete tokens for processing.

Do I need coding skills to use AudioCraft?

Yes, it is designed for ML researchers and engineers. You must clone the GitHub repository and run it via PyTorch on your own GPU. It is not a no-code solution and requires technical setup to deploy.

Can I use AudioCraft for commercial projects?

The code is released under the MIT license, but most model weights use the CC-BY-NC license. This non-commercial restriction matters for commercial use, so you should review the specific license terms for the weights you intend to deploy.

AudioCraft

✓ Editorially verified

Meta's open-source research toolkit for generating music and sound effects from text via a single autoregressive language model.

Free· Free and open source; self-hostedAudioMusicGen, AudioGen, EnCodec8.2 / 10

Visit website →

In short

AudioCraft is Meta's free, open-source toolkit for generating music and sound effects from text. It requires self-hosting on your own GPU and is best for researchers or engineers.

Best for

Pick AudioCraft if you're a researcher or engineer who wants to self-host or fine-tune state-of-the-art text-to-audio models without paying per call.

Skip if

Skip it if you want a polished web app for making finished songs - use Suno, Udio, or ElevenLabs Music instead.

AudioCraft is Meta AI's open-source framework for generative audio, bundling three models under one roof: MusicGen for text-to-music, AudioGen for environmental sound effects from text prompts, and EnCodec, a neural audio codec that compresses audio into discrete tokens. The architecture uses a single autoregressive language model operating over streams of compressed audio tokens, which simplifies training and inference compared to diffusion-based audio pipelines.

This is squarely a research release, not a polished consumer product. There's no hosted web app, no pricing tier, and no managed API on this demo page; you clone the GitHub repo (facebookresearch/audiocraft), bring your own GPU, and run it via PyTorch. That makes it a fit for ML researchers, audio engineers exploring generative pipelines, and developers who want to fine-tune or self-host text-to-music without paying per generation to a SaaS like Suno or Udio.

The models are released under permissive licenses (MIT for code, CC-BY-NC for the model weights in most cases, which matters for commercial use), and the codebase is actively referenced across the open-source audio ecosystem. If you want a click-and-go music generator, look elsewhere; if you want the underlying tech to build on, AudioCraft is one of the most cited starting points.

Editor's take

AudioCraft is the canonical open-source reference implementation for text-to-audio generation, and that's its main value. As a product it's barely one - this is a demo page for a research drop - but as a foundation for anyone building serious audio AI infrastructure, it's still hard to beat.

— The AI Tool Bible editorial team

Pros

✅ Fully open source with code and weights published by Meta
✅ Single-LM architecture is simpler than diffusion pipelines
✅ Covers music, sound effects, and neural codec in one repo
✅ Strong baseline used widely in audio ML research
✅ No usage fees once self-hosted

Cons

⚠️ No hosted product or managed API - you must run it yourself
⚠️ Model weights typically CC-BY-NC, limiting commercial use
⚠️ Requires GPU and ML tooling to operate
⚠️ Output quality trails newer commercial models like Suno v4

Use cases

text-to-musicsound-effectsaudio-compressionresearchself-hosted-generation

Frequently asked

How much does AudioCraft cost to use?: AudioCraft is completely free and open source. There are no per-call fees or pricing tiers. However, you must self-host the software, meaning you need to provide your own GPU hardware to run the models.
Is AudioCraft suitable for creating finished songs?: No, AudioCraft is a research release, not a polished consumer product. It lacks a hosted web app or managed API. If you want a click-and-go experience for finished songs, use alternatives like Suno, Udio, or ElevenLabs Music.
What models are included in the AudioCraft toolkit?: The toolkit bundles three main models: MusicGen for text-to-music generation, AudioGen for creating environmental sound effects from text prompts, and EnCodec, a neural audio codec that compresses audio into discrete tokens for processing.
Do I need coding skills to use AudioCraft?: Yes, it is designed for ML researchers and engineers. You must clone the GitHub repository and run it via PyTorch on your own GPU. It is not a no-code solution and requires technical setup to deploy.
Can I use AudioCraft for commercial projects?: The code is released under the MIT license, but most model weights use the CC-BY-NC license. This non-commercial restriction matters for commercial use, so you should review the specific license terms for the weights you intend to deploy.