MakeItTalk
MakeItTalk is open-source software that creates expressive talking-head videos from one facial image and an audio input.
What MakeItTalk is
MakeItTalk is open-source software that creates expressive talking-head videos from one facial image and an audio input. Audio content guides lip movement and nearby facial motion, while speaker information influences expressions and other head dynamics. The project describes use with portraits, paintings, sketches, 2D cartoons, manga, and stylized caricatures, including faces and characters not encountered during training. Its repository includes pretrained models, training code for modules, and Google Colab demos for natural faces. For human faces and paintings, the README calls for a centered 256×256 JPG portrait and a WAV audio file. Optional command-line settings adjust lip motion on the x and y axes and head displacement. Local use requires Python 3.6, ffmpeg, and Python packages; cartoon face warping on Ubuntu also requires winehq-stable. Creating custom puppets remains on the project to-do list, and training sections for voice conversion, the speaker-aware branch, and image-to-image translation are marked as unfinished. The software is free under a CC BY-NC 4.0 license, permitting noncommercial use subject to its terms.
Good
- Works with portraits, paintings, sketches, and stylized characters.
- Includes pretrained models and module training code.
- Provides Google Colab demos for natural faces.
- Optional settings adjust lip and head motion.
- Free under a noncommercial license.
Watch out
- Local use requires Python 3.6 and ffmpeg.
- Cartoon face warping on Ubuntu requires winehq-stable.
- Custom puppets remain on the to-do list.
- Several training sections are unfinished.
Who it suits
MakeItTalk may suit people who want to generate talking-head videos from facial images and audio, and are comfortable with its listed local requirements. Its license permits noncommercial use subject to its terms.
Verdict
MakeItTalk provides research code for generating expressive talking-head videos from an image and audio. Its noncommercial license and local setup requirements are important considerations for potential users.
Plans and prices
From MakeItTalk's own pricing page, checked 4 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Open-source research code | Free | CC BY-NC 4.0 · noncommercial use only |
The facts
Each one read from MakeItTalk's own pages, with the date it was checked.
What it does
- Available code
- The repository includes pretrained models, training code for modules, and Google Colab demos for natural faces.checked 4 Oct 2026
- Custom puppets
- The README lists creating custom puppets as a to-do item.checked 4 Oct 2026
- Image and audio input
- For human faces and paintings, the README instructs users to provide a centered 256×256 JPG portrait and WAV audio file.checked 4 Oct 2026
- License
- The repository license is Creative Commons Attribution-NonCommercial 4.0 International, which permits licensed use for noncommercial purposes subject to its terms.checked 4 Oct 2026
- Local requirements
- The README specifies Python 3.6, ffmpeg, and Python packages; cartoon face warping on Ubuntu also requires winehq-stable.checked 4 Oct 2026
- Motion controls
- Optional command-line arguments adjust lip motion along the x and y axes and head-motion displacement.checked 4 Oct 2026
- Purpose
- MakeItTalk generates expressive talking-head videos from a single facial image, using audio as the only input.checked 4 Oct 2026
- Security and privacy
- The repository page does not state security certifications or privacy practices.checked 4 Oct 2026
- Speaker-aware animation
- The method separates audio content, which controls lip and nearby facial motion, from speaker information, which influences expressions and other talking-head dynamics.checked 4 Oct 2026
- Supported imagery
- The project describes use with human portraits, paintings, sketches, 2D cartoons, manga, and stylized caricatures.checked 4 Oct 2026
- Training status
- Voice conversion, speaker-aware branch, and image-to-image translation training sections are marked “Todo...”.checked 4 Oct 2026
- Unseen inputs
- The method is described as generalizing to faces and characters not observed during training.checked 4 Oct 2026
Alternatives to MakeItTalk
- 1
Sync Labs
Free planAndroidiOSWebAPI8.0From $5 a month - 2
Morph Studio
Free planiOSWeb7.8From $12 a month - 3
VEED
Free planAndroidiOSWebExtension7.5Free plan - 4
Muse
Free planOpen sourceLinuxmacOSSelf-hostedWindows7.4Free plan - 5
CHAMELAION LipSync API
Free planWebAPI7.3From €5 a month - 6
lipsyn.cc
Free planWebAPI7.3€11.99 one-time