AI-Vtuber
一个端到端的AI主播定制模块,当前支持对接b站直播间,支持本地chatglm3和智谱api语言模型,支持so-vits-svc、gpt-sovits和bert-vits2语音模型。
Stars: 188
AI-VTuber is a highly customizable AI VTuber project that integrates with Bilibili live streaming, uses Zhifu API as the language base model, and includes intent recognition, short-term and long-term memory, cognitive library building, song library creation, and integration with various voice conversion, voice synthesis, image generation, and digital human projects. It provides a user-friendly client for operations. The project supports virtual VTuber template construction, multi-person device template management, real-time switching of virtual VTuber templates, and offers various practical tools such as video/audio crawlers, voice recognition, voice separation, voice synthesis, voice conversion, AI drawing, and image background removal.
README:
本项目旨在实现一个高自由度的可定制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。
本项目特色:
- 1.本项目对于本地显卡的要求并不高,能正常运行stable-diffusion的电脑基本都能安心食用本项目。
- 2.本项目占地面积可能会比较大(完整部署后大约20多g,还不算第三方项目),主要是因为虚拟环境体积比较大,日后会着手解决该问题。
- 3.本项目内置miniconda3管理虚拟环境,便于用户自行扩展第三方模块。
- 4.本项目提供了一个可视化的客户端(基于streamlit框架构建),支持:环境管理、虚拟主播定制、扩展项目自启动、一些实用的小工具、直播后端监听、图数据库编辑等操作。
- 5.本项目提供了对于so-vits-svc4.1项目的训练-推理一条龙服务。
- 6.本项目提供了一个后端API服务器,支持通过get/post请求获得本项目绝大多数服务。
- 7.本项目支持虚拟主播模板构建、多人设模板管理、实时切换虚拟主播模板等操作。
- 8.当前版本中,本项目对接的开源项目包括:so-vits-svc4.1(语音转换)、GPT-Sovits(语音合成)、UVR5(人声分离)、fast-whisper(语音识别)、stable-diffusion-webui(图像生成)、stable-diffusion-comfyui、easyaivtuber(数字人驱动)、rembg(背景扣除)
- 9.本项目提供的实用小工具包括:视频/音频爬虫、语音识别、人声分离、语音合成、语音转换、AI画画、图片去背景。
- 10.本项目通过构建角色提示词模板、基于知识图谱查询的认知/作品知识库、基于向量数据库的知识库查询构建AI虚拟主播人设(技术实现可以去看作者的语雀文档或者博客)。
文档教程(正在更新中)| 视频效果演示(这个是老版本的演示)|夸克网盘【提供整合包、预训练模型的下载】
本项目提供release版以及整合包版。
-
[x] 当前版本功能:
- [x] 对接哔哩哔哩开放平台
- [x] 支持edge-tts+svc实现定制化的语音合成
- [x] 支持gpt-sovits
- [x] 支持智谱api
- [x] 通过图数据库实现本地歌库多元化搜索
- [x] 通过向量数据库和知识图谱搭建知识库
- [x] 自动化的知识图谱制作工具
- [x] 支持多模板AI虚拟主播定制
- [x] 具有短期/长期记忆
- [x] 支持情感聊天
- [x] 支持对话、唱歌、本地/网络搜索、画画四种意图的任务
- [x] 对接so-vits-svc并提供训练-推理的一条龙服务
- [x] 对接sd(webui和comfyui)
- [x] 对接EasyAiVtuber项目
- [x] streamlit客户端设计(主要是管理和定制你的ai-vtuber的)
-
[ ] 当前主要工作:
- [ ] 完善项目文档(在语雀更新【附件中文档教程】)
- [ ] 录制相关使用教程(在b站更新)
- [ ] 发布与本项目相关联的第三方项目整合包(【附件中夸克网盘】)
-
[ ] **近期更新计划: **
- [ ] 支持更多的哔哩哔哩直播间弹幕互动
- [ ] 字幕机
- [ ] 支持通过与AI-VTuber的互动生成训练数据
- [ ] 支持gpt-sovits情感控制
- [ ] 对接diffsinger,实现一个完整的语音声库定制方案
- [ ] 支持更多的llm接口方案
- [ ] 支持更多的TTS接口方案
- [ ] 高级一点的AI Agent 😏
前置准备
release版需要提前下载预训练模型并将其放置于
runtime
├───miniconda3
└───pretrained_models
├───faster-whisper
└───large-v2
└───这里
├───gte-base-zh
└───这里
tools
├───uvr5
└───uvr5_weights
└───这里
在本项目根目录中,存在以下两个bat脚本
运行 condaenv.bat #本项目主环境搭建(整合包可以忽略这步)
运行 start.bat #启动客户端
清华:https://pypi.tuna.tsinghua.edu.cn/simple/
阿里云:http://mirrors.aliyun.com/pypi/simple/
中国科技大学:https://pypi.mirrors.ustc.edu.cn/simple/
华中科技大学:http://pypi.hustunique.com/simple/
上海交通大学:https://mirror.sjtu.edu.cn/pypi/web/simple/
豆瓣:http://pypi.douban.com/simple/
[流萤:睡眠状态]
https://github.com/whoiswennie/AI-Vtuber/assets/104626642/4422cde1-e6c2-4c7c-8562-f5f1d2ab5c8c
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for AI-Vtuber
Similar Open Source Tools
AI-Vtuber
AI-VTuber is a highly customizable AI VTuber project that integrates with Bilibili live streaming, uses Zhifu API as the language base model, and includes intent recognition, short-term and long-term memory, cognitive library building, song library creation, and integration with various voice conversion, voice synthesis, image generation, and digital human projects. It provides a user-friendly client for operations. The project supports virtual VTuber template construction, multi-person device template management, real-time switching of virtual VTuber templates, and offers various practical tools such as video/audio crawlers, voice recognition, voice separation, voice synthesis, voice conversion, AI drawing, and image background removal.
CGraph
CGraph is a cross-platform **D** irected **A** cyclic **G** raph framework based on pure C++ without any 3rd-party dependencies. You, with it, can **build your own operators simply, and describe any running schedules** as you need, such as dependence, parallelling, aggregation and so on. Some useful tools and plugins are also provide to improve your project. Tutorials and contact information are show as follows. Please **get in touch with us for free** if you need more about this repository.
ChatGPT-On-CS
ChatGPT-On-CS is an intelligent chatbot tool based on large models, supporting various platforms like WeChat, Taobao, Bilibili, Douyin, Weibo, and more. It can handle text, voice, and image inputs, access external resources through plugins, and customize enterprise AI applications based on proprietary knowledge bases. Users can set custom replies, utilize ChatGPT interface for intelligent responses, send images and binary files, and create personalized chatbots using knowledge base files. The tool also features platform-specific plugin systems for accessing external resources and supports enterprise AI applications customization.
FisherAI
FisherAI is a Chrome extension designed to improve learning efficiency. It supports automatic summarization, web and video translation, multi-turn dialogue, and various large language models such as gpt/azure/gemini/deepseek/mistral/groq/yi/moonshot. Users can enjoy flexible and powerful AI tools with FisherAI.
ap-plugin
AP-PLUGIN is an AI drawing plugin for the Yunzai series robot framework, allowing you to have a convenient AI drawing experience in the input box. It uses the open source Stable Diffusion web UI as the backend, deploys it for free, and generates a variety of images with richer functions.
ChatGPT-On-CS
This project is an intelligent dialogue customer service tool based on a large model, which supports access to platforms such as WeChat, Qianniu, Bilibili, Douyin Enterprise, Douyin, Doudian, Weibo chat, Xiaohongshu professional account operation, Xiaohongshu, Zhihu, etc. You can choose GPT3.5/GPT4.0/ Lazy Treasure Box (more platforms will be supported in the future), which can process text, voice and pictures, and access external resources such as operating systems and the Internet through plug-ins, and support enterprise AI applications customized based on their own knowledge base.
dify-helm
Deploy langgenius/dify, an LLM based chat bot app on kubernetes with helm chart.
FastGPT
FastGPT is a knowledge base Q&A system based on the LLM large language model, providing out-of-the-box data processing, model calling and other capabilities. At the same time, you can use Flow to visually arrange workflows to achieve complex Q&A scenarios!
GoMaxAI-ChatGPT-Midjourney-Pro
GoMaxAI Pro is an AI-powered application for personal, team, and enterprise private operations. It supports various models like ChatGPT, Claude, Gemini, Kimi, Wenxin Yiyuan, Xunfei Xinghuo, Tsinghua Zhipu, Suno-v3.5, and Luma-video. The Pro version offers a new UI interface, member points system, management backend, homepage features, support for various content formats, AI video capabilities, SAAS multi-opening function, bug fixes, and more. It is built using web frontend with Vue3, mobile frontend with Uniapp, management frontend with Vue3, backend with Nodejs, and uses MySQL5.7(+) + Redis for data support. It can be deployed on Linux, Windows, or MacOS, with data storage options including local storage, Aliyun OSS, Tencent Cloud COS, and Chevereto image bed.
self-llm
This project is a Chinese tutorial for domestic beginners based on the AutoDL platform, providing full-process guidance for various open-source large models, including environment configuration, local deployment, and efficient fine-tuning. It simplifies the deployment, use, and application process of open-source large models, enabling more ordinary students and researchers to better use open-source large models and helping open and free large models integrate into the lives of ordinary learners faster.
chatgpt-plus
ChatGPT-PLUS is an open-source AI assistant solution based on AI large language model API, with a built-in operational management backend for easy deployment. It integrates multiple large language models from platforms like OpenAI, Azure, ChatGLM, Xunfei Xinghuo, and Wenxin Yanyan. Additionally, it includes MidJourney and Stable Diffusion AI drawing features. The system offers a complete open-source solution with ready-to-use frontend and backend applications, providing a seamless typing experience via Websocket. It comes with various pre-trained role applications such as Xiaohongshu writer, English translation master, Socrates, Confucius, Steve Jobs, and weekly report assistant to meet various chat and application needs. Users can enjoy features like Suno Wensheng music, integration with MidJourney/Stable Diffusion AI drawing, personal WeChat QR code for payment, built-in Alipay and WeChat payment functions, support for various membership packages and point card purchases, and plugin API integration for developing powerful plugins using large language model functions.
easyAi
EasyAi is a lightweight, beginner-friendly Java artificial intelligence algorithm framework. It can be seamlessly integrated into Java projects with Maven, requiring no additional environment configuration or dependencies. The framework provides pre-packaged modules for image object detection and AI customer service, as well as various low-level algorithm tools for deep learning, machine learning, reinforcement learning, heuristic learning, and matrix operations. Developers can easily develop custom micro-models tailored to their business needs.
awesome-LLM-game-agent-papers
This repository provides a comprehensive survey of research papers on large language model (LLM)-based game agents. LLMs are powerful AI models that can understand and generate human language, and they have shown great promise for developing intelligent game agents. This survey covers a wide range of topics, including adventure games, crafting and exploration games, simulation games, competition games, cooperation games, communication games, and action games. For each topic, the survey provides an overview of the state-of-the-art research, as well as a discussion of the challenges and opportunities for future work.
lobe-cli-toolbox
Lobe CLI Toolbox is an AI CLI Toolbox designed to enhance git commit and i18n workflow efficiency. It includes tools like Lobe Commit for generating Gitmoji-based commit messages and Lobe i18n for automating the i18n translation process. The toolbox also features Lobe label for automatically copying issues labels from a template repo. It supports features such as automatic splitting of large files, incremental updates, and customization options for the OpenAI model, API proxy, and temperature.
prompt-in-context-learning
An Open-Source Engineering Guide for Prompt-in-context-learning from EgoAlpha Lab. 📝 Papers | ⚡️ Playground | 🛠 Prompt Engineering | 🌍 ChatGPT Prompt | ⛳ LLMs Usage Guide > **⭐️ Shining ⭐️:** This is fresh, daily-updated resources for in-context learning and prompt engineering. As Artificial General Intelligence (AGI) is approaching, let’s take action and become a super learner so as to position ourselves at the forefront of this exciting era and strive for personal and professional greatness. The resources include: _🎉Papers🎉_: The latest papers about _In-Context Learning_ , _Prompt Engineering_ , _Agent_ , and _Foundation Models_. _🎉Playground🎉_: Large language models(LLMs)that enable prompt experimentation. _🎉Prompt Engineering🎉_: Prompt techniques for leveraging large language models. _🎉ChatGPT Prompt🎉_: Prompt examples that can be applied in our work and daily lives. _🎉LLMs Usage Guide🎉_: The method for quickly getting started with large language models by using LangChain. In the future, there will likely be two types of people on Earth (perhaps even on Mars, but that's a question for Musk): - Those who enhance their abilities through the use of AIGC; - Those whose jobs are replaced by AI automation. 💎EgoAlpha: Hello! human👤, are you ready?
geekai
GeekAI is an open-source AI assistant solution based on AI large language model API, featuring a complete system with ready-to-use front-end and back-end management, providing a seamless typing experience via Websocket. It integrates various pre-trained character applications like Xiaohongshu writing assistant, English translation master, Socrates, Confucius, Steve Jobs, and weekly report assistant. The tool supports multiple large language models from platforms like OpenAI, Azure, Wenxin Yanyan, Xunfei Xinghuo, and Tsinghua ChatGLM. Additionally, it includes MidJourney and Stable Diffusion AI drawing functionalities for creating various artworks such as text-based images, face swapping, and blending images. Users can utilize personal WeChat QR codes for payment without the need for enterprise payment channels, and the tool offers integrated payment options like Alipay and WeChat Pay with support for multiple membership packages and point card purchases. It also features a plugin API for developing powerful plugins using large language model functions, including built-in plugins for Weibo hot search, today's headlines, morning news, and AI drawing functions.
For similar tasks
WristAssist
WristAssist is the first app for all WearOS watches that fully brings the classic ChatGPT and DALL-E features to your wrist. It allows users to chat, save chats, edit chats, view galleries, create images, and share images directly from their wrist. The app provides a seamless user experience with easy installation from Google Play and free lifetime updates. Users can refer to the Wiki page for detailed setup instructions. WristAssist is licensed under the terms of the Apache 2.0 license.
AI-Vtuber
AI-VTuber is a highly customizable AI VTuber project that integrates with Bilibili live streaming, uses Zhifu API as the language base model, and includes intent recognition, short-term and long-term memory, cognitive library building, song library creation, and integration with various voice conversion, voice synthesis, image generation, and digital human projects. It provides a user-friendly client for operations. The project supports virtual VTuber template construction, multi-person device template management, real-time switching of virtual VTuber templates, and offers various practical tools such as video/audio crawlers, voice recognition, voice separation, voice synthesis, voice conversion, AI drawing, and image background removal.
For similar jobs
promptflow
**Prompt flow** is a suite of development tools designed to streamline the end-to-end development cycle of LLM-based AI applications, from ideation, prototyping, testing, evaluation to production deployment and monitoring. It makes prompt engineering much easier and enables you to build LLM apps with production quality.
deepeval
DeepEval is a simple-to-use, open-source LLM evaluation framework specialized for unit testing LLM outputs. It incorporates various metrics such as G-Eval, hallucination, answer relevancy, RAGAS, etc., and runs locally on your machine for evaluation. It provides a wide range of ready-to-use evaluation metrics, allows for creating custom metrics, integrates with any CI/CD environment, and enables benchmarking LLMs on popular benchmarks. DeepEval is designed for evaluating RAG and fine-tuning applications, helping users optimize hyperparameters, prevent prompt drifting, and transition from OpenAI to hosting their own Llama2 with confidence.
MegaDetector
MegaDetector is an AI model that identifies animals, people, and vehicles in camera trap images (which also makes it useful for eliminating blank images). This model is trained on several million images from a variety of ecosystems. MegaDetector is just one of many tools that aims to make conservation biologists more efficient with AI. If you want to learn about other ways to use AI to accelerate camera trap workflows, check out our of the field, affectionately titled "Everything I know about machine learning and camera traps".
leapfrogai
LeapfrogAI is a self-hosted AI platform designed to be deployed in air-gapped resource-constrained environments. It brings sophisticated AI solutions to these environments by hosting all the necessary components of an AI stack, including vector databases, model backends, API, and UI. LeapfrogAI's API closely matches that of OpenAI, allowing tools built for OpenAI/ChatGPT to function seamlessly with a LeapfrogAI backend. It provides several backends for various use cases, including llama-cpp-python, whisper, text-embeddings, and vllm. LeapfrogAI leverages Chainguard's apko to harden base python images, ensuring the latest supported Python versions are used by the other components of the stack. The LeapfrogAI SDK provides a standard set of protobuffs and python utilities for implementing backends and gRPC. LeapfrogAI offers UI options for common use-cases like chat, summarization, and transcription. It can be deployed and run locally via UDS and Kubernetes, built out using Zarf packages. LeapfrogAI is supported by a community of users and contributors, including Defense Unicorns, Beast Code, Chainguard, Exovera, Hypergiant, Pulze, SOSi, United States Navy, United States Air Force, and United States Space Force.
llava-docker
This Docker image for LLaVA (Large Language and Vision Assistant) provides a convenient way to run LLaVA locally or on RunPod. LLaVA is a powerful AI tool that combines natural language processing and computer vision capabilities. With this Docker image, you can easily access LLaVA's functionalities for various tasks, including image captioning, visual question answering, text summarization, and more. The image comes pre-installed with LLaVA v1.2.0, Torch 2.1.2, xformers 0.0.23.post1, and other necessary dependencies. You can customize the model used by setting the MODEL environment variable. The image also includes a Jupyter Lab environment for interactive development and exploration. Overall, this Docker image offers a comprehensive and user-friendly platform for leveraging LLaVA's capabilities.
carrot
The 'carrot' repository on GitHub provides a list of free and user-friendly ChatGPT mirror sites for easy access. The repository includes sponsored sites offering various GPT models and services. Users can find and share sites, report errors, and access stable and recommended sites for ChatGPT usage. The repository also includes a detailed list of ChatGPT sites, their features, and accessibility options, making it a valuable resource for ChatGPT users seeking free and unlimited GPT services.
TrustLLM
TrustLLM is a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. The document explains how to use the trustllm python package to help you assess the performance of your LLM in trustworthiness more quickly. For more details about TrustLLM, please refer to project website.
AI-YinMei
AI-YinMei is an AI virtual anchor Vtuber development tool (N card version). It supports fastgpt knowledge base chat dialogue, a complete set of solutions for LLM large language models: [fastgpt] + [one-api] + [Xinference], supports docking bilibili live broadcast barrage reply and entering live broadcast welcome speech, supports Microsoft edge-tts speech synthesis, supports Bert-VITS2 speech synthesis, supports GPT-SoVITS speech synthesis, supports expression control Vtuber Studio, supports painting stable-diffusion-webui output OBS live broadcast room, supports painting picture pornography public-NSFW-y-distinguish, supports search and image search service duckduckgo (requires magic Internet access), supports image search service Baidu image search (no magic Internet access), supports AI reply chat box [html plug-in], supports AI singing Auto-Convert-Music, supports playlist [html plug-in], supports dancing function, supports expression video playback, supports head touching action, supports gift smashing action, supports singing automatic start dancing function, chat and singing automatic cycle swing action, supports multi scene switching, background music switching, day and night automatic switching scene, supports open singing and painting, let AI automatically judge the content.