MuseNet- developed by OpenAI- is a powerful deep neural network capable of producing 4-minute musical compositions using 10 different instruments. It has the ability to blend various styles ranging from country to Mozart to the Beatles. Similar to GPT-2- MuseNet utilizes a versatile unsupervised technology that can predict the next token in a sequence- be it audio or text. By training on MIDI file data- the model can generate samples in a desired style by providing a prompt. To enhance its contextual understanding- MuseNet incorporates multiple embeddings such as positional embeddings- timing embeddings- and structural embeddings.