yochaiye/LipVoicer

Official Code implementation for the ICLR paper "LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading"

41
/ 100
Emerging

This project helps generate speech from silent video footage, allowing you to hear what's being said even when there's no original audio. It takes a silent video as input and outputs a synchronized audio track with the spoken words. This is ideal for content creators, video editors, or archivists who need to restore or add audio to silent clips of people speaking.

No commits in the last 6 months.

Use this if you have silent video footage of someone speaking and need to generate realistic speech to accompany their lip movements.

Not ideal if you need to generate speech for videos that don't clearly show a person's lips, or if you're looking for general voice synthesis that isn't tied to a video.

video-editing content-creation video-restoration media-production speech-synthesis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

86

Forks

13

Language

Python

License

MIT

Last pushed

Sep 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yochaiye/LipVoicer"

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