talking-avatar 开源项目推荐（60 个）

Lynpoint /CyberVerse

自托管的实时数字人类代理平台。使用WebTTC、角色记忆、工具、RAG和可选的数字人视频构建语音优先的人工智能代理。

met4citizen /TalkingHead

Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.

MartinDelophy /ai-video-editor

开源、本地优先的视频编辑器，创作者和 AI 智能体可在同一条真实时间线上编辑。

PunithVT /ai-avatar-system

AI 虚拟形象/数字人平台——上传照片、克隆声音，与任意面孔进行实时对话并生成唇同步视频。开源、可自托管。Claude · Whisper · Chatterbox · MuseTalk。

ecruhue /DialogLab

DialogLab is an authoring tool for configuring and running Human-AI multi-party conversations.

kkakkkka /MambaTalk

[NeurlPS-2024] The code of MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models

XRSPACE-Inc /perxona-connect-kit

Add a talking 3D AI avatar to any web app. Samples and tools for the Perxona Connect SDK: <sv-presenter> web component, lip-sync, text-to-speech and VRM avatars. Clone to talking avatar in under 15 minutes.

rookiestar28 /ComfyUI-LongCat-Avatar

为LongCat视频化身1.5音频驱动的人类视频生成提供ComfyUI定制节点;macOS 推理分支 macOS-MLX 现已可用于苹果硅芯片的 MLX 测试。

Sgvkamalakar /Azure-Talking-Avatar

Explore the power of Azure Text-to-Speech with interactive talking avatar, Lisa 👩🏻‍🦱. Choose from multiple languages and avatar styles to bring your text to life.

albirrkarim /react-gpt-web-guide-docs

Interactable AI that have control over your frontend website, It guides your user walk around your website its a salesman / supports.

taochangle /LingCast

基于 Qwen SSE、CosyVoice3 声音克隆和 MuseTalk 1.5 唇形同步的交互式 AI 数字人直播。支持 Chrome 聊天采集、自主主持、观众节目、换装和媒体缓存。采用 Go/Gin、React/Next.js、Python、MariaDB、Redis、RustFS 和 FFmpeg/SRS。

minkhant1996 /soemind-forge

Budget-aware AI agent content studio for creating videos, images, carousels, voiceovers, music, captions, and content calendars with consistent brand assets and cost control.

Bomou-AI /Talking-Avatar

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

NavodPeiris /gsplat-talkinghead

LAM Gaussian-Splat Avatars for AI voice agents. Realistic avatars for interview/support/sales agents.

interviewflowai /talking-avatar

Give your voice agent a face. Talking Avatar turns any voice, from any text-to-speech engine or voice agent, into a lifelike talking avatar on your page, in real time.

Bomou-AI /AI-Avatar

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

tlemangen /FreeTalkDiff

[CVPR 2026] IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation

bibinkunjumon2020 /Azure-Avatar-AI

The text to speech avatar system is a text to speech feature with vision capabilities, that allow customers to create synthetic videos of a 2D photorealistic avatar speaking. The Neural text to speech Avatar models are trained by deep neural networks based on the human video recording samples, and the voice of the avatar .

Bomou-AI /Animated-Characters

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

neosapience /TA2.0

Audio-driven talking avatar and lip-sync video generation from a reference image and speech audio.