Model · Talking presenters, Video

InfiniteTalk

A free, downloadable model that makes a person in a video or photo speak along to a new audio track, moving lips, head and body to match. It can run for long clips. Built on Wan 2.1; needs a powerful graphics card and some setup. Apache 2.0 licence.

Go to InfiniteTalk’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
Weights and code under Apache 2.0.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Apache 2.0 (Permissive (e.g. Apache 2.0, MIT))
Base model Wan2.1 has its own licence (not re-checked here).
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
Apache 2.0 allows commercial use; card says the makers claim no rights over generated content and you are responsible for lawful use.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: Free to download and run yourself
Plans below.
How you use it: On your own computer, Inside another tool
Gradio demo and a ComfyUI branch; community integrations in Wan2GP and ComfyUI-WanVideoWrapper.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: MeiGen-AI
Repo and model card name the MeiGen-AI organisation only; no parent company or country stated.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A video, lips that match new audio (main use)
A talking presenter, a talking version of a photo
A video, in another language (dubbing with lip-sync)

video to videoimage to videoaudio to video

Video + audio to a lip-synced video (dubbing), or image + audio to a talking video. It doesn't translate; you supply the new audio.

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 (animate any photo or video of a person), no consent step
Runs on your own computer; no consent step.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Limits: note: 480p or 720p output. Video-to-video can run indefinitely; image-to-video is good to about 1 minute before colours drift.
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face, ComfyUI

Models it uses (not yet listed on Plainly)

Wan2.1-I2V-14B-480P (base model)

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

Arcads, Dzine, EchoMimic, FantasyTalking, HunyuanVideo-Avatar, ImagineArt, Kapwing, LatentSync, Mage Space, Magic Hour, MuseTalk, Picsart, PixVerse, Rask AI, SadTalker, SeaArt, sync., TopView, VEED, Vozo, Wav2Lip

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.