Adobe Firefly now handles audio generation, letting creators produce music, voiceovers, and sound effects without leaving the platform. This shift matters because it consolidates visual and audio workflows, reducing the need to switch between separate tools for different media types. Users can now generate professional-grade audio assets directly within the same interface they use for image editing. The update aims to bridge the gap between digital image editing and professional audio production within a single interface.
New audio tools consolidate visual and audio workflows
The software integrates specialized third-party models to power these new capabilities. Adobe has added Runway Aleph 2.0 and Kling 3.0 for video tasks, alongside Google's Gemini Omni Flash for broader generative tasks. These integrations allow Firefly to leverage external AI strengths while maintaining its own content safety framework. The company positions Firefly as a legally safer alternative for commercial use compared to competitors like Suno, Udio, and ElevenLabs.
The new Generate Music tool creates customized tracks based on user prompts. Generate Speech turns scripts into synthetic voice recordings for narration or dialogue. Generate Sound Effects produces suitable sounds for individual video scenes to enhance audio immersion. Adobe stated, "The new Generate Music, Generate Speech, and Generate Sound Effects tools have now left testing and are available to all users." This confirmation marks the end of the beta phase for these specific features.
These tools are now available globally to all Adobe Firefly users as of August 20, 2026. The release completes the expansion of Firefly from a visual-only suite into a multi-modal creative studio. Creators can now sequence audio generation alongside image and video creation in a unified workflow. The update solidifies Firefly's position as a comprehensive platform for digital content creation.
Source: NotebookCheck
