AMAAI-Lab/t2m-inferalign

Improving Symbolic Music Generation with Inference-Time Alignment

29
/ 100
Experimental

This project helps music composers, producers, and hobbyists generate symbolic music (like MIDI files) that perfectly matches their text descriptions. You input a text prompt describing the music you want, and it outputs a MIDI file that is more harmonically consistent and aligns better with the implied rhythm and key from your text. This tool is for anyone creating music from textual ideas, aiming for higher quality and accuracy.

No commits in the last 6 months.

Use this if you are generating music from text prompts and need the resulting composition to be more musically coherent and closely aligned with the semantic and rhythmic nuances of your descriptions.

Not ideal if you are looking to generate raw audio directly or if your primary focus is on developing or training new music generation models.

music-composition midi-generation music-production generative-music sound-design
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

20

Forks

1

Language

Python

License

MIT

Last pushed

Aug 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/AMAAI-Lab/t2m-inferalign"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.