General Introduction OpenVoice is a versatile method of instant speech cloning that allows you to copy the voice of a reference speaker and generate multilingual speech using only short audio clips of the speaker. In addition to copying tones, OpenVoice allows fine control over voice style, including emotion, accent, rhythm,...
Comprehensive Introduction insanely-fast-whisper is an audio transcription tool that combines OpenAI's Whisper model with various optimization techniques (e.g. Transformers, Optimum, Flash Attention) to provide a command line interface (CLI) designed to transcribe large amounts of audio quickly and efficiently. It uses Whi...
Enable Builder Smart Programming Mode, unlimited use of DeepSeek-R1 and DeepSeek-V3, smoother experience than the overseas version. Just enter the Chinese commands, even a novice programmer can write his own apps with zero threshold.
Lepton Search General Introduction Lepton Search is a conversational AI search engine, launched by Jia Yangqing and built using the Lepton AI platform.Lepton Search actively searches the web for data and organizes it into organized and logical answers based on a user's natural language questions, and comes with...
Comprehensive Introduction NextChat is a revolutionary AI chat service that allows users to deploy chat services with best-in-class language models such as GPT-3, GPT-4, GPT-4.5 and Gemini Pro. It offers an elegant user interface, collaboration features, integrations, templates and feedback analytics. In addition, its cross-platform client...
Comprehensive Introduction This is an open source project developed by Steven Tey called Novel, it is a Notion style WYSIWYG text editor , integrated AI auto-completion feature that can help users to improve the efficiency of text input . The project provides detailed documentation and installation guide to support the deployment of Vercel...
Comprehensive introduction Jina AI's Reader project is an open source tool (Reader open source address), can be any URL by adding the prefix https://r.jina.ai/转换成适合大型语言模型 (Large Language Models, LLM) input format, support for dynamic streaming mode and image reading...
Comprehensive Introduction HuixiangDou is a large-scale language model (LLM)-based group chat assistant designed to cope with group chat scenarios through a three-stage pre-processing, rejection and response process. It is able to answer user questions without causing information flooding. The project provides complete web, Android and flow...
Introducing Browse Browse AI is a no-coding cloud-based web automation software designed to help users extract and monitor data from any website without programming. You can train a bot to perform data extraction, monitoring and automation tasks with just one mouse click. And it works with over 7...
Comprehensive introduction wechat-article-exporter is an open source tool designed to help users batch export WeChat public number articles. The tool supports exporting the embedded audio and video in the article without building any environment, can 100% restore the article style, and supports private deployment. Users can use keywords or public ...
General Introduction Often I have to download YouTube and Twitter videos, so I found this free and ad-free video downloader.Cobalt is an open source media downloader designed to provide a user-friendly download experience. It supports downloading video and audio content from multiple platforms, including YouTube, Vimeo,...
In the rapid development of the Internet today, download tools as an important means for users to obtain information and resources, plays an indispensable role. In this paper, we will systematically analyze five open source download tools: AB Download Manager, XDM (Xtreme Download Manager), Aria2, qBittorrent and Mo...
General Introduction Parler-TTS is an open source text-to-speech (TTS) modeling library developed by Hugging Face, designed to generate high-quality, natural-sounding speech. The model is capable of generating speech with a specific speaker style (e.g. gender, pitch, speaking style, etc.) based on the input text.Parler-TTS ...
Comprehensive Introduction OpenAOE is an open source large model group chat framework, aiming to solve the problem of the lack of chat frameworks in the current market with multiple models responding in parallel. With OpenAOE, users can talk to multiple Large Language Models (LLMs) at the same time and get parallel output. The framework supports access to a wide range of commercial and...
Comprehensive introduction Sensitive Word Filtering Tool (Sensitive Word) is a high-performance Java sensitive word filtering tool based on the implementation of the DFA algorithm framework . The tool is able to efficiently detect and filter sensitive words , supports a variety of format conversion and custom replacement strategies. Its design goal is to provide an easy to use and performance ...
General Introduction Comics Downloader is an open source tool designed to help users download comics and comic books from various websites. The tool supports a variety of file formats, including PDF, EPUB, CBR and CBZ, enabling users to choose the appropriate format according to their needs.Comics Downloader by G...
General Introduction AnimatedDrawings is an open source project developed by Facebook Research to transform children's drawings into animated characters through automation techniques. The project is based on the paper "A Method for Animating Children's Drawings of the Human Figure...
Comprehensive Introduction Xorbits Inference (Xinference) is a powerful and comprehensive distributed inference framework that supports inference for a wide range of AI models such as Large Language Models (LLMs), Speech Recognition Models and Multimodal Models. With Xorbits Inference, users can easily deploy their own one-click...
General Introduction Wav2Lip is an open-source high-precision lip sync generation tool designed to accurately synchronize arbitrary audio with lip sync in video. The tool, released by Rudrabha Mukhopadhyay et al. at ACM Multimedia 2020, utilizes advanced AI techniques to enable various environments...
General Introduction FoleyCrafter is an open source project developed by OpenMMLab to generate vivid and synchronized sound effects for silent videos. The project uses advanced artificial intelligence techniques to analyze video content to generate semantically related and time-synchronized sound effects, thus enhancing the realism of the video and...
Genspark: deep search and writing of research reports based on Genspark intelligences2025-04-03
GPT-Crawler: Automatically Crawling Website Content to Generate Knowledge Base Documents2025-03-29
LatentSync: an open source tool for generating lip-synchronized video directly from audio2025-03-31
Qwen2.5-Omni: an end-measurement model for multimodal input and real-time speech interaction2025-03-27
GhidraMCP: A Reverse Engineering Tool to Connect AI with Ghidra2025-03-29
Mureka: AI-generated original music tool launched by Kunlun Wanwei2025-03-27
English 
简体中文 
日本語 
Deutsch 
Português do Brasil