Model · Talking presenters, Video

Wav2Lip

An older, free research model that makes the lips in any video match a new audio track. Widely copied and easy to try, but the results are low resolution and the licence allows only personal, research and non-commercial use.

Go to Wav2Lip’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Code and weights downloadable, but only for personal, research and non-commercial use.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Wav2Lip repository terms (personal/research/non-commercial) (Non-commercial only)
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: No
README: commercial use strictly prohibited because the models were trained on the LRS2 dataset; contact the authors for commercial requests.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download and run yourself for non-commercial use
Plans below.
How you use it: On your own computer
Python 3.6 and ffmpeg; Docker image and Google Colab notebooks linked.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
Our judgement: old Python version, manual weight downloads.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: IIIT Hyderabad researchers (CVIT)
Repo lists individual authors and links project pages on iiit.ac.in domains; institution not named in text. No country recorded.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
Still downloadable; not marked deprecated. Repo points commercial users to the authors' later company, Sync (sync.so), whose models it calls considerably better.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A video, lips that match new audio (main use)

video to videoaudio to video

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Rights and safety

Real faces and voices: Copies a real face (lip-sync any video), no consent step
Works on any face in a video; no consent step in self-run software.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Other options for “A video, lips that match new audio”

Arcads, Dzine, EchoMimic, FantasyTalking, HunyuanVideo-Avatar, ImagineArt, InfiniteTalk, Kapwing, LatentSync, Mage Space, Magic Hour, MuseTalk, Picsart, PixVerse, Rask AI, SadTalker, SeaArt, sync., TopView, VEED, Vozo

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.