Fosowl/SoundGan
A project for using Generative adversarial networks to generate any kind of sounds.
This project helps audio engineers, sound designers, and content creators generate unique sound effects or background audio. You provide a general type of sound you want to create, and it generates brand new audio samples. It can also gather new training data from YouTube to expand its sound generation capabilities.
No commits in the last 6 months.
Use this if you need to create novel sound assets for your projects, like unique ambient noise, instrumental snippets, or specific sound effects, without relying on existing sound libraries.
Not ideal if you need to precisely replicate an existing sound or manipulate specific parameters of an audio recording.
Stars
9
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Fosowl/SoundGan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sjcobb/ai-duet-3d
3D music animation + machine learning (in development)
Ravi-Teja-konda/AudioInsightsGenerator
Unlock AI power with AudioInsightsGenerator! From audio to summaries, emotion analysis, idea...
archinetai/audio-ai-timeline
A timeline of the latest AI models for audio generation, starting in 2023!
SolarLiner/latentwt
Generate wavetables, with AI.
Komorebirumu/awe-ms-20260316-1206-02
AI Niche Instrument Trainer: Practice & Real-time Feedback