Need royalty-free samples? Get AI to generate them
A new AI model looks to revolutionise the eternal hunt of producers in search of samples free to use in their music with AI-generated content.
Finding great samples is one of the biggest challenges facing producers. Then there are the licensing costs involved. Sample sites such as RouteNote Create offer a handy way for producers and musicians to easily find and use affordable samples, but a new source of samples may shake up the industry.
Stability AI have revealed their artificial intelligence model which generates sounds and music samples that can be used freely. It has been trained on nearly half a million royalty-free recordings to develop an idea of the sorts of sounds and music to produce. The model can produce up to 47 seconds of varied audio, created based on the text prompts you give it.
In a statement, Stability AI said: “We’re excited to announce Stable Audio Open, an open source model optimised for generating short audio samples, sound effects, and production elements using text prompts. This release marks a key milestone as we further open portions of our generative audio capabilities to empower sound designers, musicians, and creative communities.”
Their tool has the potential to offer an unlimited source of sounds for manipulation in music creation. Rather than searching tags and genre prompts, creators have the potential to write exactly what they’re looking for and – hopefully – get exactly what they want produced just for them.
Being trained on royalty-free audio also means that there is no ethical quandary over the AI model. No copyrighted content has been used to develop the AI’s algorithm and therefore no content will be produced from the inspiration of other people’s music.
Stability AI added: “While an exciting step forward, this is still just the beginning for open and responsible audio generation capabilities. We look forward to continuing research and prioritising development hand-in-hand with creative communities. Let the open exploration of AI audio begin!”