AIMS API Launches Prompt Search

AIMS API has launched Prompt Search - a new product that allows exploring music catalogues using natural language, phrases, and descriptions instead of traditional keywords and tags.

Prompt Search is revolutionary in that it makes finding the right tracks for audio-visual projects as simple and enjoyable as taking advice from a musically knowledgeable friend. All the user needs to do is type in a search describing what they are looking for; this could be a scene, location, time period, musical style or even an entire music brief. The AI developed by AIMS will then identify suitable tracks based on the audio only and deliver perfect results in seconds. Even catalogues with no keywords and tags can be searched this way, making it possible to explore entire music catalogues using natural language and discover suitable results that might otherwise stay hidden.

"It's fast, it’s accurate and it works like magic. Unlike other attempts at this type of music search, ours genuinely works," said Martin Nedved, CEO and founder of AIMS API. "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 and makes searching much more enjoyable and accurate."

Established in Prague in 2019, and now with representatives in West and East Coast USA, London and Copenhagen, AIMS was developed by music publishing and sync company owners with a deep understanding of the creative industries.

The introduction of Prompt Search takes the future of music search and discoverability to an entirely new level by providing a fast, reliable, and intuitive solution that benefits record labels, publishers, production music catalogues, broadcasters and TV and film companies. It also benefits content creators, playlist curators and music supervisors by maximising music discoverability and minimising the amount of time and effort needed to find the perfect track.

Several proprietary technologies were used in the making of Prompt Search, and its development builds on over 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.

"It really is miraculous," he said. "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."