Music production meta-tool AudioCraft releases open source AI tool

On August 2, Eastern Time, Meta released a generative AI tool called AudioCraft, which allows users to create music and audio using text prompts

AudioCraft consists of three main components:

MusicGen: Trained with Meta owned/specially licensed music to generate music based on text prompts.

AudioGen: Use public sound effects for training to generate audio or expand existing audio, and subsequently generate environmental sound effects (such as dog barking, car horns, footsteps on wooden floors).

EnCodec (improved version): Neural network-based audio compression codec that can generate higher quality music and reduce artifacts, or perform lossless compression of audio files.

Official claims that AudioCraft can stimulate the creativity of musicians and sound designers, helping them quickly get inspiration and improve their works in innovative ways

The above is the detailed content of Music production meta-tool AudioCraft releases open source AI tool. For more information, please follow other related articles on the PHP Chinese website!