crlandsc/tiny-audio-diffusion

A repository for generating and training short audio samples with unconditional waveform diffusion on accessible consumer hardware (<2GB VRAM GPU)

38
/ 100
Emerging

This tool helps music producers and sound designers create short, high-quality audio samples like drum hits. You can feed it existing audio samples to train new models, and it outputs unique, studio-grade sound effects or one-shot instruments. This is ideal for independent musicians, game sound artists, or anyone who needs custom audio assets but has limited computing power.

183 stars. No commits in the last 6 months.

Use this if you want to generate short, high-fidelity audio waveforms or train custom sound models using only an average consumer-grade GPU.

Not ideal if you need to generate long musical pieces, complex audio arrangements, or if you require very fast generation times without compromising sample length.

music-production sound-design audio-synthesis electronic-music sample-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

183

Forks

16

Language

Python

License

MIT

Last pushed

Jun 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/crlandsc/tiny-audio-diffusion"

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