Adobe has made three Firefly AI audio tools generally available, letting creators generate music, voiceovers and sound effects without leaving the app.
Following previews at last year’s Adobe MAX and a lengthy development period, Adobe has made three Firefly AI audio tools generally available: Generate Music, Generate Speech, and Generate Sound Effects
Available in both the desktop and mobile web versions of Firefly, here’s what they do:
Generate Music, powered by Adobe's Firefly Music Model, creates original tracks matched to a video's length and mood. Adobe says the tracks are fully licensed for commercial use, with no separate music-licensing subscription required.
Generate Speech, powered by the Firefly Speech Model, produces voiceovers with control over voice, pacing, and emotion. The tool includes an optional integration with ElevenLabs.
Generate Sound Effects, powered by the Firefly Audio Model, generates custom sound effects synced to the timing and action of a video.
The company has also debuted Firefly AI Assistant on a new free tier, though it is bounded by daily generation limits. It also features two new skills, Create Storyboard and Create Brand Kit, as well as expanded batch editing and branded mockup generation.
Firefly’s roster of third-party models has also been further expanded with the addition of Gemini Omni Flash, which supports multimodal prompting across video, audio, image, and text inputs. Firefly already offers models from Google, Kling AI, Luma AI, OpenAI, Runway, and ElevenLabs, as it pursues its strategy of allowing as much user choice in this area as possible.