Adobe announces Project Music GenAI Control, an experimental AI-based music generation tool

Adobe announced a new experimental artificial intelligence (AI)-based tool on Wednesday that can generate music from simple text prompts. Called Project Music GenAI Control, Adobe says the AI ​​tool not only generates music, but also gives users “pixel-level control over music,” allowing them to edit, extend, shorten, remix and create loops. There are more editing options available that allow detailed control over the generated clip. Adobe’s latest AI tool arrives after the company last week announced an AI assistant for Acrobat and Reader that can summarize and analyze long PDF files.

Project Music GenAI Control, according to Adobe message, is a music creation and editing interface that works like most other AI tools. Users are given a text box where they can add plain text prompts such as “happy rock song,” “intense hip-hop beats,” or “sad jazz.” Once the input is submitted, the AI ​​will generate a music video based on the request made. There are no voices in the generated clip; only musical instruments. But that’s only part of what this underdeveloped platform can do.

According to Adobe, once the music track is created, users can access multiple editing tools to change the way the music sounds. Some of these tools can change intensity, texture, tempo, and more at any point in the clip. Users can further customize it to their liking by extending its length and adding another sequence to the music, remixing part or the entire clip or even turning it into a loop.

One specific feature of the AI ​​music generator is that it allows users to change the sound using a reference melody, which can be any modern or classical music. After doing this, the user can change the style and genre of the music. Adobe says this deep control over the generated clip makes it easy to use as a video intro, for podcasts, to create songs and music tracks, and more.

As for data privacy, Adobe claims it only used publicly available data to train its AI model. The company hasn’t shared any details about the base model’s architecture or interface, so no other details are known. It’s worth mentioning that Adobe isn’t the only player in the AI ​​music generation space. Google has its own music generator called MusicLM which is under development and Meta has its AudioCraft which is an open source AI model for music generation and is available on GitHub.