1. OpenAI is developing a new tool that generates music based on text and audio prompts, potentially for use in videos or with vocal tracks.
2. The company is working with students from the Juillard School to annotate scores as training data for this tool.
3. While OpenAI has previously launched generative music models, its recent focus has been on text-to-speech and speech-to-text audio models; other competitors in this field include Google and Suno. (Additional comment from OpenAI is pending.)
2. The company is working with students from the Juillard School to annotate scores as training data for this tool.
3. While OpenAI has previously launched generative music models, its recent focus has been on text-to-speech and speech-to-text audio models; other competitors in this field include Google and Suno. (Additional comment from OpenAI is pending.)
Similar Readings (5 items)
Conversation: OpenAI reportedly developing new generative music tool
OpenAI Introduces Voice Cloning Tool, But Waits for Public Release
US firm develops generative AI capable of reproducing a human voice
OpenAI Announces New Video Generator
Conversation: OpenAI ramps up developer push with more powerful models in its API
Summary
OpenAI is developing a text-to-music tool, utilizing student annotations from Juilliard School for training. Despite previous focus on text-to-speech and speech-to-text audio models, this new project aims to generate music for videos or vocal tracks. Competitors in this field include Google and
Statistics
80
Words1
Read CountDetails
ID: ed42fc70-c218-4202-898e-9e695a62ab81
Category ID: listed_summary
URL: https://techcrunch.com/2025/10/25/openai-reportedly-developing-new-generative-music-tool/#summary
Date: Oct. 26, 2025
Notes: 2025-10-26
Created: 2025/10/26 06:42
Updated: 2025/12/07 23:26
Last Read: 2025/10/26 12:47