Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Face-based Speech Generation on LRS3 (test)

4.14MOS

Vclip

Updated 1mo ago

Evaluation Results

Method	Links
Vclip 2026.01		4.14
Face-TTS 2026.01		2.46

SOTA Paper

Vclip

Vclip: Face-based Speaker Generation by Face-voice Association Learning

Dataset

LRS3

Follow for update

@wizwand_team Discord

Related Benchmarks

Face-voice cross-modal verification on Vox1 (test)Voice Cloning on LRS3 (test)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs