London, UK (August 3, 2023)—AI-powered music search company AIMS API has launched Prompt Search, which enables the exploration of music catalogs using natural language, phrases and descriptions instead of traditional keywords and tags.
According to the company, Prompt Search allows users to type in a search describing what they are looking for; it could be a scene, location, time period, musical style or an entire music brief. The AI developed by AIMS will then reportedly identify suitable tracks based on the audio only and deliver results in seconds.
AIMS claims catalogs with no keywords and tags can be searched this way, making it possible to explore entire music catalogs using natural language and discover results that might otherwise stay hidden.
Beat Machine Merges Studio Gear, Video Gaming
Martin Nedved, CEO and founder of AIMS API, noted, “We are confident that once people try Prompt Search, they will not want to go back. Traditional keyword searches will always have limitations placed upon them by the humans who initially tag the music. Prompt Search removes those limitations.”
Established in Prague in 2019, and now with representatives in the USA, London and Copenhagen, AIMS was developed by music publishing and sync company owners.
Several proprietary technologies were used in the making of Prompt Search, and its development builds on five years of research undertaken by AIMS API. Howie Ross, music taxonomy researcher at AIMS API who played a key role in the creation of Prompt Search, says he was surprised by language AI’s ability to take a natural phrase and turn it into musical suggestions: “When I began experimenting with this technology, I typed in the phrase ‘tumbleweed rolling along an empty highway’. The machine immediately understood what I had in mind—a sort of Ry Cooder, Paris, Texas vibe—and delivered a list of tracks that were ideal. I was amazed. I didn’t describe any instruments or moods—just scenery—and yet it was able to convert that simple command into something musical. From there, I was able to skip through its suggestions until I found a track I liked. I then used Similarity Search to identify even more tracks that fitted my brief.”
