OpenAI reportedly building AI music generator from text and audio
It sounds like
OpenAI is cooking up something new in the audio kitchen! Word on the street is they're developing a tool that'll let you create music from text and audio prompts. Imagine just typing in "a chillwave track for a sunset drive" and, bam, you've got a tune! Think about the possibilities. Aspiring filmmakers could easily add soundtracks to their projects. Or, if you're a singer but lack instrumental skills, you could generate a backing track with a few clicks. It's pretty wild to consider. Now, it's unclear if this will be a standalone app or integrated into something like ChatGPT or Sora. Also, a source mentioned that
OpenAI is collaborating with Juilliard students to dissect and annotate musical scores, presumably to feed data into their AI model. OpenAI isn't new to generative music, but their previous efforts came before the ChatGPT craze. Lately, they've been focusing on text-to-speech and speech-to-text tech. Of course, they aren't the only players in this space; Google and Suno are also experimenting with similar technology. I'm curious to see where this goes and how it stacks up against the competition. If it becomes as easy as using chatGPT, the future of music creation may change forever.
