skirdey/voicerestore

VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration

42
/ 100
Emerging

This project helps you clean up noisy or degraded voice recordings. You provide an audio file with issues like background noise, reverberation, or distortion, and it outputs a clearer, restored version of the speech. This is ideal for anyone working with audio, such as podcasters, researchers analyzing interviews, or content creators improving voiceovers.

199 stars. No commits in the last 6 months.

Use this if you need to significantly improve the clarity and quality of degraded speech audio recordings, regardless of the type or intensity of imperfections.

Not ideal if you need to clean up music or other non-speech audio, as the model is specifically optimized for human voice.

audio-restoration podcast-production voiceover-editing interview-analysis speech-enhancement
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

199

Forks

20

Language

Python

License

MIT

Last pushed

Apr 21, 2025

Commits (30d)

0

Get this data via API

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

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