Meta has shared their Audiocraft neural network — it can create music based on a text description or a test segment 🎶

It works impressively, expect an inflow of beatmakers with samples from classical music.

#Meta ⚡️ #Audio ⚡️ #NeuralNetwork

The new AudioLDM 2 neural network generates any sounds, sound effects, speech and even music in different styles.

The model is based on a universal representation of sound, allowing large-scale self-supervised pre-training of the basic latent diffusion model without sound annotation and combining the advantages of autoregressive and latent diffusion models.

One more thing: it knows how to generate sound from pictures.

Source code repo.

#service #useful #audio #aigeneration