audio-driven 开源项目推荐（18 个）

Kedreamix /Awesome-Talking-Head-Synthesis

💬 An extensive collection of exceptional resources dedicated to the captivating world of talking face synthesis! ⭐ If you find this repo useful, please give it a star! 🤩

Tencent-Hunyuan /HunyuanCustom

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Advocate99 /DiffGesture

[CVPR'2023] Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation

wwjjqq888888-pixel /nanfeng-h3-comfyui

NanFeng H3 V10 all-in-one ComfyUI node: multi-reference media, AI storyboards, audio drive & continuous second pass | 南风H3 V10多参、智能分镜、音频驱动与连续二采

AISHIWEILAI /syncanimation

[IJCAI 2025] This is the official source for our paper "SyncAnimation: A Real-Time End-to-End Framework for Audio-Driven Human Pose and Talking Head Animation"

OranDuanStudy /LRCM

LRCM: Listen to Rhythm, Choose Movements — Autoregressive Multimodal Dance Generation via Diffusion and Mamba

neosun100 /infinitetalk-deployment

Production-ready deployment for MeiGen-AI InfiniteTalk & MultiTalk models with Docker, auto-download, and Gradio UI

gantasmo /Lip-Sync-Avatars

The WAV2LIP-GAN Lip Sync App is a web-based application that allows users to generate lip-synced videos by aligning facial movements in an avatar image with an uploaded audio file. Using the powerful WAV2LIP-GAN model, the app ensures high-quality, synchronized facial animations, even for arbitrary faces and audio inputs.

svllvsxprod /LipFlow

Portable desktop UI for advanced Wav2Lip lip-sync workflows on Windows. Beautiful interface, face selection, tracking, timeline editing, job queue, ultra-quality presets, and local inference.

Lulzx /fast-lipsync

Close-to-real-time MuseTalk lip-sync on Apple Silicon

T-64 /gs-avatar

Real-time audio-driven talking head with 3D Gaussian Splatting (~65 fps)

DioBey7 /Project-Hunter-AI

Advanced Enemy AI System for Unity (C#). Features a Modular Behavior Tree, Custom A* Predictive Ambush, and Audio-Driven state machines.

kaniyeFelix /infinitetalk-deployment

🚀 Deploy InfiniteTalk and MultiTalk models effortlessly with automated management, Docker support, and a user-friendly Gradio interface.

nawta /video-retalking_legacy

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

hiroki-abe-58 /ComfyUI-LeapTalk

Unofficial ComfyUI integration of LeapTalk: turn a portrait and speech into a talking video locally (official weights and 1-step recipe, separate runtime)

skyphusion-labs /vivijure-musetalk

MuseTalk lip-sync finish engine for Vivijure on RunPod GPU. Pairs with vivijure-cf or vivijure-local.

RichardSneyd /ua-engine

An engine for developing interactive, audio-driven learning games and activities using HTML5; Leverages PIXI.js for rendering & Howler for audio.

simongonzalezdc /voice-to-scultpure-app

Voice-to-Sculpture Studio - turn voice into 3D-printable sculptures in the browser with real-time audio analysis, WebLLM, and STL/GLB export.