Yue AI is an open-source music generation model. The user can input lyrics and genre information as text, along with optional audio clips for context, with the input audio clips needing to be around 30 seconds long. Supported input languages include English, Mandarin Chinese, Cantonese, Japanese, and Korean. Yue AI will output its generated music in an audio file that is up to 5 minutes in length.
Year: 2025
Website: https://map-yue.github.io/
Input types: Audio Text
Output types: Audio
Output length: 5 minutes
AI Technique: Transformer
Dataset: WeNetSpeech, LibriHeavy, GigaSpeech, 650K hours of internet mined data
License type: Apache-2.0 license
Real time:
Free:
Open source:
Checkpoints:
Fine-tune:
Train from scratch:
For Windows, you can use Pinokio. For Linux, watch this tutorial video. For MacOS, this is a tutorial.