An innovative office product that integrates cutting-edge AI technology and efficient office functions. Through deep integration of model download, model dialogue, knowledge base management, image generation, speech-to-text, text-to-speech, and comprehensive image processing capabilities, GodoAI It achieves full coverage of office scenarios, allowing every user to enjoy the convenience and efficiency brought by intelligence. ?A conscientious product with unique ingenuity. The core functions are fully localized and can be easily controlled with only 8G memory.
English | Simplified Chinese
API
Windows users :
Windows (AMD64) Web version Desktop version
Windows (ARM64) Web version Desktop version
MacOS users :
MacOS (AMD64) Web version
MacOS (ARM64) Web version
Linux users :
Linux (AMD64) Web version
Linux (ARM64) Web version
Note: Start the server after downloading the web version. The access address is: http://localhost:56710/.
Built-in rich AI model library, users can download the required models with one click according to their needs
Zero configuration, no need to register, download and use
Pure golang development backend, low resource consumption and high performance
Cross-platform, can be installed on Windows, Linux, and MacOS, no docker deployment required
Github
Gitee
Built-in rich AI model library, users can download the required models with one click according to their needs
Covers almost all basic large models on the market, including chat models, text-to-picture, picture-to-text, picture-to-picture, text-to-speech, speech-to-text, Embeddings and other models
Supports uploading of most types of files and can capture remote web pages
Support local vector database
Comprehensive functions, including full process management from title setting to content editing, saving, and exporting
Supports associated knowledge bases, allowing you to create anything without limiting the length, giving you unlimited space.
Supports paragraph generation, selected generation and all generation
After the creation is completed, it can be exported directly to word
Supports viewing the creation list, configuring prompt advanced settings, etc.
Generate images without a GPU graphics card
Use StableDiffusion to quickly generate high-quality images to meet the needs of various scenarios such as design, advertising, and marketing.
Supports all models in SD and supports customizing parameters in SD
Supports tabbed generation of prompts
The generated pictures will be automatically saved locally, and the back-end generation logs can be viewed in real time.
Support multi-modal model dialogue
Support saving chat content
Support custom chat parameters
Support associated knowledge base
Large models can translate into multiple languages
Support custom translation parameters
It is recommended to choose the telespeech model when converting voice to text, which supports multi-regional dialect recognition. Different models have different speech recognition languages.
Supports speech-to-text and text-to-speech functions, allowing you to quickly communicate with large models without typing.
Supports voice-to-text function, meeting minutes and interview notes can be easily processed.
Supports saving meeting records for subsequent management and viewing.
Front-end build
cd frontend i pnpm build
Backend build
# go install github.com/wailsapp/wails/v2/cmd/wails@latestwails build# wails build -nsis -upx //you need install nsis and upx
