# OpenAI Releases Jukebox: AI That Generates Music with Singing

OpenAI has unveiled Jukebox, a neural network capable of generating original music as raw audio, complete with rudimentary singing voices. The AI can produce songs across multiple genres and mimic various artist styles.

The company is making Jukebox fully open-source, releasing both the model weights and code to the public. They've also provided a tool that lets users explore samples the AI has created.

**Why it matters:** This represents a significant leap in AI-generated content. Unlike previous music AI that worked with MIDI or simple melodies, Jukebox creates actual audio from scratch, including vocals. This could democratize music creation, allowing anyone to generate original compositions in different styles.

The open-source release means researchers and developers can build upon this technology, potentially leading to new creative tools for musicians and producers. However, it also raises questions