Adobe’s new Project Music GenAI tool is basically Photoshop for music
“It’s a kind of pixel-level control for music,” says senior research scientist Nicholas Bryan.
Credit: Adobe Stock/ _veiksme_
Adobe has unveiled Project Music GenAI Control, an early-stage generative AI music generation and editing tool that seeks to transform how you create and edit custom audio and music.
While AI music generators have mushroomed in recent years – see Google’s MusicLM and Meta’s open-source AudioCraft – Project Music GenAI’s built-in editing features sets it apart from its peers.
Announced on Wednesday’s Hot Pod Summit in Brooklyn, Adobe’s new “experimental” tool allows creators to generate music using text prompts and have fine-grained control to edit that audio within the same workflow.
Users begin by inputting a text prompt, like “powerful rock”, “happy dance”, or “sad jazz” to generate their desired music. Once the audio is generated, you can customise the results by adjusting the music’s tempo, structure, intensity or by repeating patterns of a specific section. You can also extend the length of a track, remix selected parts, or generate a seamlessly repeatable loop for your content needs.
Besides simplifying your workflow, the new tool also allows you to say goodbye to manually cutting existing music to make intros, outros, and background audio.
“With Project Music GenAI Control, generative AI becomes your co-creator. It helps people craft music for their projects, whether they’re broadcasters, or podcasters, or anyone else who needs audio that’s just the right mood, tone, and length,” says Nicholas Bryan, a senior research scientist at Adobe Research.
“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. It’s a kind of pixel-level control for music.”
