texttoaudio

Text-to-audio models were the talk of the town before text-to-image models stole the show. However, the research to improve the first one continues, proof of this is with the recent publication of Google’s MusicLM model and its recent publication in arXiv: “ MusicLM: Generation of music from text”. Different AI models have been previously developed …

Google Research introduces MusicLM, a new text-to-audio model Read More »