Ikaros-521 / AI-Vtuber
AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊天。它使用TTS技术【edge-tts/VITS/elevenlabs/bark/bert-vits2/睿声】生成回答并可以选择【so-vits-svc/DDSP-SVC】变声；指令协同SD画图。
☆3,115Updated last week
Related projects ⓘ
Alternatives and complementary repositories for AI-Vtuber
- VirtualWife是一个虚拟数字人项目，支持B站直播，支持openai、ollama☆1,988Updated 3 weeks ago
- Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LL…☆2,044Updated last month
- Bark Voice Cloning and Voice Cloning for Chinese Speech☆2,790Updated 3 months ago
- 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…☆2,588Updated last week
- AI吟美-人工智能主播-Vtuber☆584Updated 2 months ago
- 本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动 作过渡，使合成的唇…☆1,880Updated last year
- ☆580Updated 10 months ago
- 数字人资料整理☆460Updated 2 weeks ago
- AGI 社交网络 Bot. BiliBili | 直播聊天数字人 | 视频@自动回复 | 私信bot | 终端聊天 | 语音交互☆575Updated 7 months ago
- 官方推荐的 ChatTTS 资源汇总项目，整理了全网相关资源和常见问题 || Officially recommended ChatTTS resource collection project☆1,234Updated 4 months ago
- A simple VITS HTTP API, developed by extending Moegoe with additional features.☆821Updated last week
- 🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。☆2,102Updated 4 months ago
- GPT-vup BIliBili | 抖音 | AI | 虚拟主播☆1,191Updated last year
- MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting☆2,859Updated this week
- Chat with any character you like: ChatGLM2+SadTalker+Voice Cloning | 和喜欢的角色沉浸式对话吧：ChatGLM2+声音克隆+视频对话☆588Updated last year
- This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion☆4,753Updated 4 months ago
- 一个高自由度的端到端的可定制AI-VTuber。支持对接哔哩哔哩直播间，以智谱API作为语言基座模型，拥有意图识别、长短期记忆（直接记忆和联想记忆），支持搭建认知库、歌曲作品库，接入了当前热门的一些语音转换、语音合成、图像生成、数字人驱动项目，并提供了一个便于操作的客户端。☆326Updated last month
- Makes your AI vtuber☆461Updated 2 months ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆6,327Updated this week
- EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning☆2,951Updated this week
- 每个人都能用的数字人☆700Updated 2 weeks ago
- vits2 backbone with multilingual-bert☆8,011Updated this week
- [ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis☆1,068Updated 4 months ago
- Live2D Virtual Human for Chatting based on Unity☆580Updated last year
- Fay is an open-source digital human framework integrating language models and digital characters. It offers retail, assistant, and agent …☆9,222Updated this week
- Real time interactive streaming digital human☆3,940Updated this week
- 本项目意图在于让使用各类语音合成引擎的方式变得统一，支持多种语音合成引擎适配器，允许直接作为模组使用或启动后端服务☆650Updated 7 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,163Updated 9 months ago
- 可对接fay数字人的ue5工程☆475Updated 3 weeks ago