Adobe Firefly Expands Generative AI Capabilities with Music, Speech, and Sound Effects
Adobe has expanded its Firefly creative AI studio by introducing three new audio generation capabilities: Generate Music, Generate Speech, and Generate Sound Effects. These tools are now available to all users, allowing them to create audio assets directly within a single workspace. This update streamlines the workflow for content creators by eliminating the need to switch between multiple applications or AI models for video and audio production. Additionally, the generated music is designed to be commercially safe, offering creators peace of mind regarding copyright issues. The Generate Speech feature is powered by either the Firefly Speech Model or ElevenLabs' technology, enabling text-to-speech conversion with adjustable voice, speed, and emotion. Meanwhile, the Generate Music tool focuses on instrumental background tracks tailored to video duration and vibe, rather than vocal songwriting.
## BACKGROUND
Adobe Firefly is a suite of generative AI models integrated into Adobe's creative applications, designed to generate high-quality images, vector graphics, and now audio. ElevenLabs is a leading artificial intelligence company founded in 2022 that specializes in realistic, deep learning-based speech synthesis and text-to-speech technology.