Many technology giants continue to make strides in the field of artificial intelligence. parent company of Facebook and Instagram meta and one of them. The company, led by Mark Zuckerberg, announced a few weeks ago that it had developed its own special chip for artificial intelligence.

Now another step in artificial intelligence has come from Meta. Meta’s Audiocraft research team MusicGen announced an open-source language model called

MusicGen can generate music from text

The MusicGen model, which we can call the audio version of ChatGPT, new music with text commandscan produce. Users can use the model by defining the desired music style. They can also add an existing melody if they wish.

A video shared by artificial intelligence researcher Felix Kreuk on Meta reveals what MusicGen is capable of. The video shows that music has already been added, and this music can then be changed by entering a command. In another video, “without using any pre-made sound”Pop dance number suitable for the beach with catchy melodies, tropical percussions and cheerful rhythmsIt seems that a sound can be made by typing the command ”.

research group, about 12 seconds Includes Shutterstock and Pond5 tracks, along with 10,000 high-quality music from an internal data set for training the sound reproduction model 20,000 hours used licensed music. It is possible to access a demo via MusicGen’s Hugging Face AI.

The use of artificial intelligence in music production is rapidly increasing. A few months ago, Google announced a new artificial intelligence model called MusicLM that turns lyrics into music.