Sound clipping: Himalaya's natural human voice, multi-narrator audio creation platform
综合介绍 喜马拉雅音频编辑器是一个综合性的AI音频创作平台。它提供了强大的功能，支持用户进行专业级的podcast制作、多轨录音、音频编辑，并且能将文字转换成语音。平台还含有多选项的专业语音，助力用户...
Sorting
Questgen: smart quiz question generator, AI generated multiple choice, judgment, fill in the blanks questions
综合介绍 Questgen 是一款由人工智能驱动的测验生成工具，能够从任意文本中快速生成多种类型的测验题目。无论是多项选择题、判断题、填空题还是高阶问题，Questgen 都能在几秒钟内完成生成。该工...
Retrieval based Voice Conversion WebUI: A Framework for Retrieval-based Voice Conversion | Simulating Real-life Singing Voices
综合介绍 Retrieval based Voice Conversion WebUI是一个基于VITS的简单易用的语音转换框架，可以实现任意说话人之间的语音转换，包括歌曲的翻唱和实时的变声。它具有低...
ViiTor AI: Audio/Video Multilingual Translation Synthesis and Speech Cloning Service
Comprehensive Introduction ViiTor AI is a powerful artificial intelligence platform focused on providing high-quality video translation, voice cloning, AI-generated avatar videos, and speech synthesis services. The platform supports multiple languages and is designed to help users easily realize multilingual content creation.ViiTo...
Replit Agent: Intelligent Programming Assistant
综合介绍 Replit Agent是由Replit公司推出的一款AI编程工具，旨在通过自然语言处理技术帮助用户构建软件项目。用户只需提供简单的指令或问题（Prompt），Replit Agent便能自...
Memary: an open-source project to enhance Agent long-term memory using knowledge graphs
General Introduction Memary is an innovative open source project focused on providing long-term memory management solutions for autonomous intelligences. The project helps intelligences break through the limitations of traditional context windows to achieve smarter interaction experiences through knowledge graphs and specialized memory modules.Memary adopts...
Smart Composer: Obsidian plugin for smart writing and semantic search for referencing local notes
综合介绍 Smart Composer 是一款专为 Obsidian 笔记软件设计的智能写作助手插件。它利用人工智能技术，提供上下文感知的聊天助手、智能写作辅助和一键编辑功能。该插件能够根据用户的笔记...
Cerebras: the world's fastest AI inference, high-performance computing platform available today
综合介绍 Cerebras是一家致力于推动人工智能和高性能计算领域的公司。其核心产品包括全球最快的AI推理平台和高性能计算加速器。Cerebras平台能够训练多种模型，从多语言大模型到医疗聊天机器人...
Fineshare Singify: quickly make AI cover songs, celebrity clone voice covers
综合介绍 Fineshare Singify是一个在线人工智能歌曲封面生成器。无需任何技能门槛，你可以在该网站上轻松创建你最喜欢的歌手或角色的AI封面。提供三种简单方法生成歌曲封面：搜索歌曲，上传音频...
ClipZap AI Face Swap Tool: fast AI face swap for photos and videos (free)
General Description ClipZap AI Face Replacement Tool is a leading AI face replacement tool designed for photo and video face replacement needs. The site utilizes advanced AI technology to automatically recognize people in videos and images and perform high-quality face replacement. Whether it's creating funny emoji...
Story-Adapter: generating continuous and consistent graphic illustrations based on a long story
综合介绍 Story-Adapter 是一个创新的故事可视化框架，它能够将文本故事转换为连贯的图像序列。这个项目由研究人员开发，采用了无需训练的迭代方法来生成高质量的故事插图。该框架的特点是能够处理长...
Hume AI: Empowering AI with Emotion Recognition | Recognizing Emotional States from Sounds and Expressions | Generating Speech with Emotional States
General Introduction Hume AI is an AI company focused on emotional intelligence, developing multimodal AI technologies that understand and respond to human emotions. Its flagship product, the Empathic Voice Interface (EVI), is able to recognize and respond to a user's...
Carbon: Quickly Generate Code Snippets into Images for Sharing
综合介绍 Carbon是一个在线工具，致力于将源代码转换为美观的图片，适合在社交媒体上分享。用户可以自定义图片的语法主题、字体样式等，还可保存片段以供日后使用。支持将代码直接导入，编辑并生成图片，包括...
World Labs: Build a 3D model of the world from a single image, apply for the Spatial Intelligence model beta test!
综合介绍 World Labs是一家专注于空间智能的人工智能公司，致力于构建大型世界模型（Large World Models, LWMs），以感知、生成和交互3D世界。由世界知名的AI技术先驱李飞飞...
PosterGenerator: AI-driven simple poster generator, just enter simple prompts and choose the poster style!
综合介绍 PosterGenerator是一款在线AI海报生成工具，旨在帮助用户轻松创建专业级别的海报。无论是用于商业推广、活动宣传还是个人项目，PosterGenerator都能通过简单的文本输入生...
PDF to Podcast: Convert PDF to Podcast Utility
综合介绍 受 Notebook LM 的播客生成特性和最近的 Open Notebook LM 开源实现的启发。在本食谱中，我们将实现一个关于如何构建 PDF 到播客管道的详细步骤。 给定任何 PDF...
QAnything: Local Knowledge Base Q&A System with Highly Integrated RAG Processing Flow
QAnything Comprehensive Introduction QAnything (Question and Answer based on Anything) is a local knowledge base Q&A system launched by NetEase, which supports all kinds of file formats and databases, and can be installed and used offline....
Illuminate: the AI tool that turns academic papers into audio podcasts
综合介绍 Illuminate 是谷歌推出的一款创新工具，旨在将复杂的学术论文转化为引人入胜的音频对话。通过使用谷歌的 LLM Gemini 模型，Illuminate 能够生成论文摘要和问答，并通过...
Easy Voice Toolkit: AI Voice Toolkit for Local Deployment
Comprehensive Introduction Easy-Voice-Toolkit is a multifunctional toolkit based on the Open Source Speech Project, providing a variety of automated audio tools for speech recognition, speech transcription, speech conversion, dataset creation and model training. Users can selectively use these tools as needed...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil