Adobe's generative AI tools, such as generative fill, have transformed the photo editing game. Now, Adobe is attempting to do the same but for audio with a new AI audio editing platform.
On Wednesday, the Adobe Research Team unveiled Project Music GenAI Control, an early-stage generative AI music generation and editing tool that allows users to generate music from text prompts, with AI acting as a music co-creator.
Also: The best AI image generators
Like with other text-to-music generators, Project Music GenAI Control, will enable users to enter a simple text prompt such as "powerful rock," "happy dance," "intense hip hop" or a reference melody to have a new music track output within seconds.
However, the biggest highlight of Adobe's take is that users can adjust the track for elements such as intensity, tempo, structure, repeating patterns, and more, directly within their workflow, as seen in the video below.
Additionally, users can ask the platform to loop the audio, fade it out, or extend a track, which is especially ideal for video creators who often struggle to find a track that meets the length and needs of their video.
"One of the exciting things about these new tools is that they aren't just about generating audio -- they're taking it to the level of Photoshop by giving creatives the same kind of deep control to shape, tweak, and edit their audio," says Nicholas Bryan, senior research scientist at Adobe Research. "It's a kind of pixel-level control for music,"
Also: I tried Copilot Notebook: Microsoft's new AI tool offers two handy prompt features
Adobe Research is still developing Project Music GenAI Control in collaboration with colleagues at the University of California, San Diego, and as a result, the tool is not generally available to the public yet. However, if you want to try a music generation tool for yourself there are some tools you can test now, such as MusicFX by Google and Stable Audio by Stability AI.