RoySheffer/im2wav

Official implementation of the pipeline presented in I hear your true colors: Image Guided Audio Generation

40
/ 100
Emerging

This project helps content creators, multimedia artists, or game developers automatically generate realistic audio that matches visual content. You provide an image or a sequence of images (like from a video), and it outputs semantically relevant sound. This is useful for anyone needing to quickly add appropriate soundscapes or effects to visuals without manual sound design.

124 stars. No commits in the last 6 months.

Use this if you need to generate contextually appropriate audio from images or videos, such as creating sound effects for static scenes or background audio for short video clips.

Not ideal if you need precise control over every detail of the generated audio or if your visuals require highly specific, niche sound effects not easily inferable from general image semantics.

multimedia-production sound-design content-creation game-audio digital-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

124

Forks

15

Language

Python

License

MIT

Last pushed

Jan 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/RoySheffer/im2wav"

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