Adobe launches generative AI music, speech, and sound tools in Firefly

Adobe has officially released new audio generation tools within its Firefly creative AI studio. The update introduces three primary capabilities: Generate Music, Generate Speech, and Generate Sound Effects, all of which are now generally available for commercial use.

The Firefly Music Model allows users to create original tracks tailored to the length and mood of a video. For narration, the Firefly Speech Model—alongside an option for ElevenLabs—converts text into natural-sounding speech with adjustable emotion and pacing. Additionally, the Firefly Audio Model enables the creation of custom sound effects based on specific scene descriptions.

Adobe has also enhanced its Firefly AI Assistant, moving beyond the beta phase to offer free daily generations for certain features. New functionalities include tools for creating storyboards and brand kits to streamline creative workflows for social media, vlogs, and short films.