Skip to content
Tech News
← Back to articles

Adobe Firefly’s music, voiceover, and sound effects generation tools now generally available

read original more articles
Why This Matters

Adobe Firefly’s new tools for generating music, voiceovers, and sound effects mark a significant advancement in AI-powered content creation, offering creators fully licensed, customizable audio assets that streamline production and reduce legal risks. This development empowers video producers, marketers, and musicians to enhance their projects more efficiently and affordably, fostering innovation across the industry.

Key Takeaways

Users can now create fully licensed tracks, voiceover, and sound effects on Adobe’s Firefly AI assistant. Here are the details.

Adobe recently conducted a survey in partnership with Berklee College of Music to understand the workflows and challenges faced by video creators, musicians, and marketers. According to Adobe, 100% of respondents said they use music in their videos, with 32.7% using AI-generated music. 43.2% cited legal and copyright risks as the main barrier to using music, while 38.9% cited licensing costs.

Today, Adobe is making the Generate Music tool generally available on Firefly, alongside two other tools: Generate Speech and Generate Sound Effects:

Generate Music creates original, fully licensed tracks tuned to your video’s length and mood, so your music can go wherever your content does without worrying about licensing or takedowns.

Generate Speech turns a script into clear, natural voiceovers. You can choose from Adobe’s own Firefly speech model or ElevenLabs.

Generate Sound Effects creates custom sounds that match the action, timing and energy of your content.

The company stresses that Generate Music creates fully licensed music that is ready for finished work, and like Generate Speed and Generate Sound Effects, does not require a separate subscription to generate commercially safe material.

Generate Music can analyze the contents of a video, and create editable prompts based on what it identifies as the best fit for it. Users can also adjust parameters such as the music tempo, energy, and duration before hitting Generate to receive four options in return.

When using the Generate Speech effect, users can add expressivity and pronunciation tags to certain parts of the script, while Generate Sound Effects lets users fill in a text prompt or record a sound effect with their voice to use as a reference for the generated audio.

Here’s Adobe:

... continue reading