InspireMusic
Support music generation tasks with long-form and high audio quality, sampling rates up to 48kHz.
Github:
https://github.com/FunAudioLLM/InspireMusic/
Available music generation models:
InspireMusic-1.5B-Long
,
InspireMusic-1.5B
,
InspireMusic-Base
,
InspireMusic-1.5B-24kHz
,
InspireMusic-Base-24kHz
. Both on Huggingface and ModelScope.
Currently only support English text prompts.
This page is for demo purpose, if you want to generate long-form audio, e.g., 5mins, please try to deploy locally. Thank you for your support.
Select Model Name
Chorus Mode
Output Audio Sample Rate (Hz)
Generate Audio Length (s)
↺
10
300
Input Text (For Text-to-Music Task)
Experience soothing and sensual instrumental jazz with a touch of Bossa Nova, perfect for a relaxing restaurant or spa ambiance.
Input Audio Prompt (For Music Continuation Task)
Drop Audio Here
- or -
Click to Upload
Generated Music
Text to Music
Music Continuation