haidog-yaqub/EzAudio

High-quality Text-to-Audio Generation with Efficient Diffusion Transformer

46
/ 100
Emerging

This project helps sound designers, content creators, and educators quickly generate high-quality audio from text descriptions. You provide a text prompt describing the desired sound, and it outputs a corresponding audio file. It also supports editing existing audio, like replacing a section based on new text, or generating audio that matches a reference.

330 stars.

Use this if you need to create realistic sound effects, background audio, or short audio clips from text without recording or extensive sound design software.

Not ideal if you require precise musical composition, human speech generation, or extremely long-form audio content.

sound design content creation audio production media editing education resources
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

330

Forks

25

Language

Python

License

MIT

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/haidog-yaqub/EzAudio"

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