OpenAI is reportedly developing an innovative tool that generates music from text and audio prompts, as detailed by The Information. This tool could enhance existing videos by adding music or provide guitar accompaniments to vocal tracks. While the launch date remains unspecified, it’s uncertain if the tool will be a standalone product or integrate with OpenAI’s ChatGPT and video application, Sora. To refine its models, OpenAI is collaborating with students from the Juilliard School to annotate music scores for training data. Although OpenAI has previously released generative music models, these were created before the advent of ChatGPT. The company’s recent focus has shifted towards audio models for text-to-speech and speech-to-text applications. Other competitors in the generative music space include Google and Suno. TechCrunch has sought further comments from OpenAI regarding this development. This potentially groundbreaking tool could revolutionize music generation for creators and users alike.
Source link
Share
Read more