Sign in Submit site

Talking Face Avatar

github.com/Yazdi9/Talking_Face_Avatar Video Editing & Animation Open-source projectOpen source

This project generates talking-face avatars for characters and game assets using deepfake techniques, according to its repository description.

Visit Talking Face Avatar
github.com/Yazdi9/Talking_Face_Avatar
Talking Face Avatar homepage screenshot

About Talking Face Avatar

Talking Face Avatar is an open-source repository that generates talking-face avatars for characters and game assets using deepfake techniques. Its documented workflow takes a single portrait image and an audio file and produces a talking-head video. The README describes sourcing the portrait from Leonardo.ai and the audio from ElevenLabs text-to-speech, either through their websites or their APIs.

The repository includes a Gradio web interface started with app.py, a command-line inference.py script, and a Colab notebook. It also documents a still mode for generating natural full-body video and an optional GFPGAN enhancer for improving output quality. Setup requires Python, conda, a CUDA-specific PyTorch build, and ffmpeg, and the installation steps are written for Linux. Pretrained model files must be downloaded separately, and the optional TTS package for the web demo must be installed manually. Text and image prompts entered into the Leonardo.ai and ElevenLabs steps are processed by those third-party services.

Key features

  • Generates a talking-head video from one portrait image and one audio file
  • Optional GFPGAN enhancer to improve the quality of generated video
  • Still mode for generating a natural full-body video
  • Gradio web interface launched with app.py
  • Command-line inference.py script for animating portrait images
  • Script for downloading the required pretrained model files
Best for: Developers and technical artists who are comfortable setting up Python and CUDA environments and running deep learning models locally.
Good for
  • Provides both a web interface and command-line scripts
  • Includes a Colab notebook option
  • Source code is published as an open-source repository with a LICENSE file
Watch out for
  • Installation steps are written for Linux and require a manual Python and CUDA setup
  • Pretrained model files must be downloaded separately
  • The optional TTS package must be installed manually for the web demo

Talking Face Avatar at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026
video generationprompt engineeringconversational aiavatar generation

Popular in Video Editing & Animation

Well-known listings from the same topic.

All 261
Animakeranimaker.com8mb.video8mb.videoASM Lessonsgithub.com/FFmpeg/asm-lessonsCuttrcuttr.inVideo Cuttervideo-cutter-js.comFreeMoCapfreemocap.org
Related topicsDesign Assets & InspirationImage Creation & Editing3D, CAD & MotionStock Photos & VisualsCharts & Data VisualizationColor ToolsScreen Recording & Streaming ToolsPhotography

Talking Face Avatar FAQ

What inputs does the tool need to produce a talking-head video?
The basic command takes an audio file through --driven_audio and a source image or video through --source_image. Results are saved in the results folder as MP4 files.
How are the pretrained models set up?
The README says to run the script scripts/download_models.sh, which places the model files in the folders the project expects.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 12, 2026 · How we rank