Shulou(Shulou.com)11/24 Report--

Thank you, Mr. Air, a netizen of CTOnews.com, for your clue delivery! CTOnews.com, August 3, Meta opened up a generative AI tool, AudioCraft, to help users create music and audio through text prompts.

According to the official Meta, AudioCraft contains three core components:

MusicGen: use Meta-owned / specially licensed music for training and generate music according to text prompts.

AudioGen: use public sound effects for training to generate audio or expand existing audio, followed by ambient sound effects (such as dog barking, car sirens, footsteps on the wooden floor).

EnCodec (improved version): a neural network-based audio compression decoder that can generate higher quality music and reduce human traces, or lossless compression of audio files.

After the tool is open source, relevant researchers and practitioners can use their own datasets to train the model. Officials claim that AudioCraft models can consistently generate high-quality audio over a long period of time and are easy to use, providing "inspiration" for musicians and sound designers to quickly brainstorm and "iterate their works in new ways".

As previously reported by CTOnews.com, Meta opened up the AI language model MusicGen in June, which is based on Google's Transformer model launched in 2017. As the name of the model suggests, MusicGen is mainly used for music generation, which converts text and existing melodies into complete music.

Demo video:

AudioCraft project address: click here to go

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.