Adobe AI Tool Converts Simple Sounds Into Realistic Audio Effects
Adobe is rolling out new generative AI features for filmmakers, offering creative ways to produce sound effects and steer AI-generated video. Beyond the standard text prompts used to direct Adobe's Firefly AI models, creators can now use vocalized sound effects—like spoken "boom" or "whoosh"—to generate custom audio, and use reference clips to influence the motion in videos created by Firefly.
The beta release of the Generate Sound Effects tool in the Firefly app works with both recorded and AI-generated footage, giving users more precise audio control compared to options like Google's Veo. Its interface mimics a video editor's timeline, letting users synchronize newly created sounds with their uploaded video. For instance, while watching a clip of a horse walking, a user could say "clip-clop" in rhythm with its steps and add the text description "hooves on concrete." The tool then produces four different sound effect options to pick from.
This feature expands on the Project Super Sonic demo Adobe showcased last October. It isn’t designed for speech, but it can create impact sounds—such as breaking twigs, footsteps, or zipper noises—as well as ambient backgrounds like nature scenes or city hum.
Adobe is also introducing advanced controls for its Firefly Text-to-Video generator. With Composition Reference, users can upload a video along with their text prompt to replicate that clip’s framing and camera angles in the AI-generated output, making it simpler to get the desired result without repeatedly tweaking text descriptions. Keyframe cropping allows users to crop and upload images for the start and end frames, which Firefly uses to generate the video in between. New style presets offer a range of visual aesthetics to apply quickly, including anime, vector art, claymation, and others.

Examples of style presets designed to guide the output of Adobe's AI video generation. Image: AdobeThese style presets currently work only with Adobe’s own Firefly video AI model. Based on a live demo, the results aren’t perfect—for example, the “claymation” preset resembled early-2000s 3D animation. However, Adobe continues to integrate support for competing AI models within its tools. Alexandru Costin, Adobe’s Generative AI lead, told The Verge that similar controls and presets may become available for third-party AI models down the line. This move signals Adobe’s effort to maintain its leading position in creative software as AI tools gain traction, even if its own generative models aren’t always on par with those from leaders like OpenAI or Google.
Related article
WordPress.com now allows AI agents to write and publish posts, plus more
WordPress.com, the popular web hosting and publishing platform, is now embracing AI agents—a move that could reshape the look and feel of the web. The company announced Friday that it will allow AI agents to draft, edit, and publish content on custom
Kakao Mobility outlines Level 4 autonomous driving roadmap for physical AI
Kakao Mobility is planning to develop Level 4 autonomous driving technologies internally as part of its physical AI strategy.
At the 2026 World IT Show conference in Seoul's COEX, Kim Jin-kyu — vice president and head of Kakao Mobility's Physical AI
Barry Diller: Trust in Sam Altman irrelevant as AGI nears
Barry Diller, the billionaire media titan, does not believe OpenAI CEO Sam Altman is untrustworthy, despite recent reports suggesting otherwise. Speaking at the Wall Street Journal's "Future of Everything" conference this week, Diller defended Altman
Related Special Topic Recommendations
Comments (1)
0/500
Sound design is the unsung hero of filmmaking! This tool allowing us to sketch audio with simple vocalizations is a game-changer. It lowers the barrier for indie creators who might not have a huge sound library 🎙️. But I do wonder, as these models get better, will we start losing the art of foley and the unique 'imperfect' textures created by real-world objects?
Adobe is rolling out new generative AI features for filmmakers, offering creative ways to produce sound effects and steer AI-generated video. Beyond the standard text prompts used to direct Adobe's Firefly AI models, creators can now use vocalized sound effects—like spoken "boom" or "whoosh"—to generate custom audio, and use reference clips to influence the motion in videos created by Firefly.
The beta release of the Generate Sound Effects tool in the Firefly app works with both recorded and AI-generated footage, giving users more precise audio control compared to options like Google's Veo. Its interface mimics a video editor's timeline, letting users synchronize newly created sounds with their uploaded video. For instance, while watching a clip of a horse walking, a user could say "clip-clop" in rhythm with its steps and add the text description "hooves on concrete." The tool then produces four different sound effect options to pick from.
This feature expands on the Project Super Sonic demo Adobe showcased last October. It isn’t designed for speech, but it can create impact sounds—such as breaking twigs, footsteps, or zipper noises—as well as ambient backgrounds like nature scenes or city hum.
Adobe is also introducing advanced controls for its Firefly Text-to-Video generator. With Composition Reference, users can upload a video along with their text prompt to replicate that clip’s framing and camera angles in the AI-generated output, making it simpler to get the desired result without repeatedly tweaking text descriptions. Keyframe cropping allows users to crop and upload images for the start and end frames, which Firefly uses to generate the video in between. New style presets offer a range of visual aesthetics to apply quickly, including anime, vector art, claymation, and others.

These style presets currently work only with Adobe’s own Firefly video AI model. Based on a live demo, the results aren’t perfect—for example, the “claymation” preset resembled early-2000s 3D animation. However, Adobe continues to integrate support for competing AI models within its tools. Alexandru Costin, Adobe’s Generative AI lead, told The Verge that similar controls and presets may become available for third-party AI models down the line. This move signals Adobe’s effort to maintain its leading position in creative software as AI tools gain traction, even if its own generative models aren’t always on par with those from leaders like OpenAI or Google.
WordPress.com now allows AI agents to write and publish posts, plus more
WordPress.com, the popular web hosting and publishing platform, is now embracing AI agents—a move that could reshape the look and feel of the web. The company announced Friday that it will allow AI agents to draft, edit, and publish content on custom
Barry Diller: Trust in Sam Altman irrelevant as AGI nears
Barry Diller, the billionaire media titan, does not believe OpenAI CEO Sam Altman is untrustworthy, despite recent reports suggesting otherwise. Speaking at the Wall Street Journal's "Future of Everything" conference this week, Diller defended Altman
Sound design is the unsung hero of filmmaking! This tool allowing us to sketch audio with simple vocalizations is a game-changer. It lowers the barrier for indie creators who might not have a huge sound library 🎙️. But I do wonder, as these models get better, will we start losing the art of foley and the unique 'imperfect' textures created by real-world objects?





Home






