The musicgen model is a text-to-audio transformation AI that generates music based on specific input parameters. The user can define characteristics such as top_k, top_p, a music prompt (e.g., "lo-fi guitar"), the duration of the music piece, temperature, whether to create a new piece or continue an existing one (continuation), and output format, among other parameters. After processing the user's request, the model outputs a URL where the generated music, in WAV format, can be accessed and listened to. The model represents a practical application of AI in the creation of customized music, and it can be utilized in music production, entertainment, and other related sectors.

Use cases

The MusicGen AI model is an innovative tool that could revolutionize the music industry. Its core functionality is to generate an audio file from text-based parameters, such as the desired style and duration of the music piece. For example, its use may span from solo artists who need background music for their performances to film producers looking for original soundtracks for their movies. In addition, it could serve as a valuable tool for music therapy, generating personalized soothing sounds based on user preferences. Beyond entertainment, it could also find application in an educational context, assisting music teachers as they tutor their students by creating study material in real time tailored to the students' learning pace and style. In commercials or marketing campaigns, businesses could use MusicGen to create unique jingles at reduced costs. The possible commercial products which could be developed based on this model may range from music-generating apps to comprehensive web platforms, offering a variety of services, for example, for the advertisement industry or for online content creators in need of copyright-free sounds.



Cost per run
Avg run time

Creator Models


Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Musicgen model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameMusicgen
Deployment of Meta's MusicGen
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-