NIX Solutions: Adobe’s Super Sonic AI – Sound from Text and Voice

At the annual Max conference, Adobe introduced Super Sonic, an experimental AI-powered tool that generates sound effects and background audio for video projects using text and voice input. This prototype offers multiple functionalities, including recognizing objects, analyzing voice characteristics, and generating customized audio in real-time.

NIX Solutions

Justin Salamon, head of Adobe AI, explained the team’s vision: “We wanted to give our users control over the process […] to go beyond the original text-to-sound workflow, and that’s why we worked on an audio app that really gives you precise control over energy and timing and turns it into an expressive tool.”

Key Features of Super Sonic

Super Sonic identifies objects in video sequences and translates them into sound prompts, producing relevant audio effects. It also analyzes voice features, allowing users to generate sounds by clapping, playing instruments, or interacting in other creative ways—not limited to voice input.

As part of Adobe’s tradition of showcasing experimental features at the Max conference, many tools like Super Sonic are initially presented as prototypes. Some eventually make their way into Adobe Creative Suite, such as Adobe Premiere. Although Super Sonic is currently in a demo phase, we’ll keep you updated on its development and potential integration into Adobe’s offerings.

Super Sonic’s Origins and Market Competition

Super Sonic’s developers were also involved in creating Firefly’s Generative Extend, which allowed short videos to be lengthened, including synchronized audio. However, the concept of generating sound from text or voice is not entirely new—tools like those offered by ElevenLabs are already available on the market, notes NIX Solutions.

While Adobe’s Super Sonic may not be revolutionary, its potential as a creative tool integrated within Adobe’s ecosystem could make it a valuable asset for content creators.