# 32kHz high-fidelity

MAGNeT is a non-autoregressive Transformer-based text-to-music and sound effects generation model capable of producing high-quality audio samples from text descriptions.

MAGNeT is a text-to-music and text-to-sound model capable of generating high-quality audio samples based on text descriptions. It is a non-autoregressive Transformer model based on masked generation, using a 32kHz EnCodec tokenizer.

MAGNeT is a text-to-music and text-to-sound model capable of generating high-quality audio samples from text descriptions.

MAGNeT is a text-to-music and text-to-audio model capable of generating high-quality audio samples from text descriptions.