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

Adobe has announced the general availability of three new generative AI audio tools within its Firefly platform: Generate Music, Generate Speech, and Generate Sound Effects. These tools are designed to consolidate creative workflows by allowing users to produce professional-grade audio directly within the Firefly workspace, reducing the need to switch between specialized third-party applications.

Generate Music uses the Firefly Music Model to create original, universally licensed, and royalty-free instrumental tracks tailored to a video’s specific length, mood, and genre. Generate Speech enables users to convert text scripts into natural-sounding voiceovers with adjustable pacing, emotion, and pronunciation across more than 20 languages; this feature includes an optional integration with ElevenLabs. Generate Sound Effects allows creators to produce custom audio matched to the timing and energy of visual content through text prompts or reference audio.

In addition to the audio suite, Adobe is expanding its Firefly ecosystem by adding Gemini Omni Flash to its roster of third-party models, which supports multimodal prompting across text, image, video, and audio. The company is also introducing a new free tier for the Firefly AI Assistant, which includes daily generation limits and new capabilities such as creating storyboards and brand kits.