Samplab has announced the release of a free software that uses uses Meta’s MusicGen model weights to let users generate short samples from a text prompt.
Our goal with TextToSample is to enable the producer community to experiment with state-of-the-art generative AI models. We want to show what’s currently possible with these models, especially when running them locally on your computer. TextToSample’s purpose is certainly not to replace human musicians, which it’s not capable of doing anyway.
TextToSample is available to download as a VST3 plugin and as standalone software for Windows and macOS.
More information: Samplab
