sony/soundctm

Pytorch implementation of SoundCTM

37
/ 100
Emerging

This project helps audio engineers, sound designers, and content creators generate realistic, full-band sound effects or audio clips from simple text descriptions. You provide a textual prompt (e.g., "a dog barking in a park") and it outputs a corresponding audio file. It's for anyone needing to create custom soundscapes or effects without needing to record or synthesize them manually.

101 stars. No commits in the last 6 months.

Use this if you need to quickly generate specific sound effects or ambient audio based on text descriptions for multimedia projects, games, or virtual environments.

Not ideal if you need fine-grained control over musical composition, voice synthesis, or extremely long, complex audio narratives.

sound design audio generation content creation multimedia production game audio
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

101

Forks

10

Language

Python

License

MIT

Last pushed

Mar 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sony/soundctm"

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