AI-Media2Doc is an open source AI video graphic creation assistant designed to help users convert audio and video content into multiple styles of documents with one click. The project was developed by hanshuaikang, hosted on GitHub, adopts the MIT license, supports local deployment, and protects user privacy.
An open source Web tool based on the AI model aims to convert video and audio content into multiple styles of documents with one click, including small red books, public accounts, knowledge notes, mind maps, etc.
Project introduction
AI-Media2Doc provides a Web tool based on the AI macro model and capable of converting video and audio content into:
- Picture and text notes in the style of Xiaohongshu
- Articles on Weixin Official Accounts
- Knowledge Notes
- mind map
- video caption
- Various document forms such as content summary
The tool does not require login registration, and the front and back terminals can be deployed locally. Users can experience AI video/audio to document services at a very low cost.
Core functions
- Fully open source: Adopt the MIT protocol and support local deployment, making it convenient for users to customize according to their needs.
- Privacy protection: No login and registration are required, and task records are stored locally to ensure the security of user data.
- Front-end processing: Using ffmpeg wasm technology, there is no need to install ffmpeg locally, improving convenience of use.
- Multiple styles support: Support multiple document styles such as small red books, public accounts, knowledge notes, mind maps, and content summaries to meet the needs of different scenarios.
- AI Dialogue: Support AI secondary Q & A for video content to improve the interactivity and depth of content.
- Subtitle export: Supports conversion of video content into subtitles for subsequent editing and publishing.
🚀Usage
Users can deploy the tool locally by cloning the GitHub repository. The specific steps include:
Clone warehouse:
$git clone https://github.com/hanshuaikang/AI-Media2Doc.git
Go to the project directory and start the service:
$cd AI-Media2Doc
$docker-compose up
Access locally deployed services in a browser, upload audio and video files, select the required document style, and generate corresponding document content.
Project address
You can visit the project on GitHub for more information and the latest updates:
👉AI-Media2Doc GitHub repository
Github：https://github.com/hanshuaikang/AI-Media2Doc
Oil tubing: