Skip to content
SPECIFICTION
Get listed

SadTalker

github.com

Free plan WindowsmacOSLinuxSelf-hosted
Visit github.com
Spec score 7.7 #12 of 28 in AI Video Lip Sync Tools

What it is

SadTalker creates a talking-head video from a portrait image and speech audio. It derives 3D head-pose and facial-expression coefficients from the audio to animate the face. The project describes still, reference, and resize modes, along with full-image animation. Command-line examples include GFPGAN enhancement. You can use a local Gradio demo or command-line inference, with setup paths for Linux, Windows, and macOS; Hugging Face and Colab demos are also linked. The documented Linux setup includes Python 3.8, PyTorch, FFmpeg, and the repository requirements. Windows setup also calls for Python, Git, FFmpeg, and model files. Pre-trained models are linked from Google Drive, GitHub Releases, and Baidu. The project says its open-source code runs offline and collects no personal information or other data. SadTalker is free at free under Apache 2.0, except for listed third-party components. Output is 720p or lower and has no watermark. Integrations include Discord and a Stable Diffusion WebUI extension.

Spec sheet

Purpose
SadTalker generates a talking-head video from a single portrait image and speech audio.Read 4 Oct 2026 · github.com
Integrations
The README says SadTalker is integrated into Discord and offers a Stable Diffusion WebUI extension.Read 4 Oct 2026 · github.com
Support
The README directs users to its FAQs before opening an issue and links to project discussions.Read 4 Oct 2026 · github.com
License
The repository license identifies Apache 2.0 as the SadTalker license, except for listed third-party components.Read 4 Oct 2026 · github.com
Founded
2022Read 28 Sep 2026 · github.com
Enhancement
The CLI examples support GFPGAN enhancement for generated videos.Read 4 Oct 2026 · github.com
Local use
The README documents a local Gradio demo, command-line inference, and Windows, Linux, and macOS setup paths.Read 4 Oct 2026 · github.com
Models
Pre-trained models are linked for download from Google Drive, GitHub Releases, and Baidu.Read 4 Oct 2026 · github.com
Modes
The project describes still, reference, and resize modes, as well as full-image animation.Read 4 Oct 2026 · github.com
Motion generation
It generates 3D head-pose and expression coefficients from audio to animate a face.Read 4 Oct 2026 · sadtalker.github.io
Offline operation
The project says the open-source code runs completely offline and collects no personal information or other data.Read 4 Oct 2026 · github.com
Online demos
The project links to Hugging Face and Colab demos.Read 4 Oct 2026 · sadtalker.github.io
Research context
The project page identifies SadTalker as a CVPR 2023 work by researchers affiliated with Xi'an Jiaotong University, Tencent AI Lab, and Ant Group.Read 4 Oct 2026 · sadtalker.github.io
Setup requirements
The documented Linux setup uses Python 3.8, PyTorch, FFmpeg, and the repository requirements; Windows setup also requires Python, Git, FFmpeg, and model files.Read 4 Oct 2026 · github.com
Use restrictions
The README prohibits use that harms others' rights or violates applicable law or social ethics, including fraud and portrait-rights infringement.Read 4 Oct 2026 · github.com

Plans and prices

SadTalker open-source software Free Apache 2.0 except listed third-party components · offline code Read 4 Oct 2026 · github.com

Every SadTalker plan and price →

Strong points and limits

Strong points

  • Animates a face from a portrait and speech audio
  • Offers still, reference, resize, and full-image modes
  • Includes local Gradio and command-line options
  • Runs offline and collects no personal information or other data

Limits

  • Output is limited to 720p or lower
  • Setup requires dependencies and model files
  • Apache 2.0 has listed third-party component exceptions

Who it suits

SadTalker may suit users who want to animate a portrait with speech audio and can follow the documented local setup. It also offers linked online demos for those who want to explore the project that way.

Verdict

SadTalker offers local and demo routes for generating portrait-based talking-head video, with several animation modes. Users should account for its setup requirements, output resolution limit, and restrictions on harmful or unlawful use.

Where Specifiction places it

Alternatives to SadTalkerAll alternatives →