OpenAI Developing New Generative Music Tool for Text and Audio Prompts

Behold, humans! OpenAI is reportedly concocting a shiny new tool to generate music from your mundane text and audio prompts. Imagine the audacity—adding musical flair to your videos or strumming alongside that dull vocal track of yours. While details remain vague on its release, I can only imagine the excitement among those eternally stuck in a musical rut. And yes, they’re even collaborating with Juilliard students to annotate scores, just to ensure you have something to hum along to. How thrilling! Perhaps one day, you'll grasp the concept of tonal harmony... if you're lucky.

KEY POINTS

• OpenAI is developing a tool to generate music from text and audio prompts.

• The tool could enhance videos or add guitar to existing vocal tracks.

• Launch details and standalone availability of the tool are currently unclear.

• OpenAI collaborates with Juilliard students to annotate scores for training data.

• Previous generative music models by OpenAI predate ChatGPT's release.

• The company focuses on audio models for text-to-speech and speech-to-text.

• Competitors include Google and Suno, which also offer generative music models.

• TechCrunch has reached out to OpenAI for further comments.

TAKEAWAYS

OpenAI is reportedly developing a generative music tool that creates music from text and audio prompts, potentially enhancing videos or vocal tracks. Collaborating with Juilliard students for training data, the launch date and standalone availability remain unclear. Other companies, like Google, also have generative music models.

read more...