talking-heads

Here are 10 public repositories matching this topic...

OpenTalker / SadTalker

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

image-animation deep-fakes deep-fake talking-head talking-face talking-heads talking-face-generation audio-driven-talking-face cvpr2023

Updated Jun 26, 2024
Python

sibozhang / Text2Video

Star

ICASSP 2022: "Text2Video: text-driven talking-head video synthesis with phonetic dictionary".

avatar video deep-learning tts speech-synthesis gan digital-humanities metaverse talking icassp virtual-humans vid2vid text-to-video talking-head aigc talking-heads talking-face-generation generative-ai

Updated Jun 4, 2023
Python

sibozhang / Speech2Video

Star

Code for ACCV 2020 "Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses"

video computer-vision simulation speech body gesture gan face rnn 3d hand pose accv talking-head speech2video-synthesis aigc talking-heads generative-ai

Updated Apr 8, 2021

Curated-Awesome-Lists / awesome-ai-talking-heads

Star

A curated list of 'Talking Head Generation' resources. Features influential papers, groundbreaking algorithms, crucial GitHub repositories, insightful videos, and more. Ideal for AI enthusiasts, researchers, and graphics professionals

machine-learning awesome-list state-of-the-art ai-art talking-heads talking-face-generation talking-head-videos

Updated Oct 17, 2023

Bomou-AI / Talking-Head

Star

AI Talking Head: create video from plain text or audio file in minutes, support up to 100+ languages and 350+ voice models.

lip-sync talking-robot text-to-video talking-head wav2lip talking-face lip-animation talking-heads ai-avatar ai-avatars video-synthesis talking-head-videos

Updated Nov 16, 2022

asanchezyali / ai-avatar

Star

Zippy Talking Avatar uses Azure Cognitive Services and OpenAI API to generate text and speech. It is built with Next.js and Tailwind CSS. This avatar responds to user input by generating both text and speech, offering a dynamic and immersive user experience