Speech Recognition
Henry-23/VideoChat
实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.
PythonMITupdated Dec 18, 2025
🏆 #2,203 overall#284 of 793 in Speech Recognition🔥 active this week
PunithVT /ai-avatar-system
🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.
$ git clone https://github.com/PunithVT/ai-avatar-system.gitStars
577
577
This week
—
Forks
145
145
Language
Python
License
MIT
Created
Nov 30, 2025
1.0 years old
Last push
Nov 13, 2026
🔥 this week
Categories
More in Speech Recognition
Speech Recognition
honwee/mynah
Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统
GoApache-2.0updated Oct 24, 2026
Speech Recognition
PeterH0323/Streamer-Sales
Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端🗝️、Docker-compose 打包部署🐋
🔍 Search & Retrieval🤖 Language Models
PythonAGPL-3.0updated Mar 8, 2025
Speech Recognition
rudrankriyam/Foundation-Models-Framework-Lab🔥 active
A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.
🔍 Search & Retrieval🤖 Language Models
SwiftMITupdated Nov 7, 2026
Speech Recognition
Sallyn0225/eidolon-sc🔥 active
和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）
🔍 Search & Retrieval
PythonAGPL-3.0updated Nov 13, 2026
Speech Recognition
artcc/freelingo🔥 active
Open-source, self-hosted AI language learning platform with local or cloud LLMs, CEFR study plans, an AI tutor, voice conversations, flashcards, and spaced repetition.
JavaScriptAGPL-3.0updated Nov 12, 2026
Data from GitHub · snapshot Nov 13, 2026