lipsynth-experiment. End-to-end pipeline generates speech from silent lip videos using LLMs and audio-visual cues, combining "AVI-Talking" and "Towards Accurate Lip-to-Speech Synthesis in-the-Wild" techniques, enabling synthesis from visual cues alone without audio/transcripts.

github.com/zoharbabin/lipsynth-experiment

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.