An open source, general-purpose AI agent that runs on your machine as a desktop app, CLI, or embeddable API, for code and non-code tasks.
YILS-LIN/short-video-factory
Open-source cross-platform desktop app that generates short marketing videos from text prompts and footage, with AI copywriting, TTS voiceover and automatic batch editing.
Open-source alternative to:CapCut
- Stars
- 5,768
- Forks
- 802
- Open issues
- 19
- Last commit
- 4 days ago
What is it?
Short Video Factory is a desktop application for producing product marketing and general-interest short videos with little manual editing. You provide a text prompt and a set of video clips, and the app generates the script with an AI model, converts it to speech, and assembles the clips with subtitles into a finished video.
The copywriting step works with any service that exposes an OpenAI-compatible API. Voiceover is generated with Edge TTS, and the tool supports batch tasks that keep producing videos automatically from a preset configuration. Multiple languages, including Chinese and English, are supported.
The app runs locally on Windows, macOS and Linux. It is built with TypeScript and is licensed under AGPL-3.0. Some items on the roadmap, such as finer parameter control, more TTS providers and richer subtitle effects, are still planned.
Key features
- 01Generates marketing scripts from prompts via OpenAI-compatible APIs.
- 02Converts scripts to speech with EdgeTTS.
- 03Automatically combines footage, audio and subtitles into finished videos.
- 04Runs batch tasks that keep producing videos from a preset configuration.
- 05Runs on Windows, macOS and Linux.
Use cases
- Producing product promotion videos for e-commerce listings.
- Making batches of general-interest short videos for social platforms.
- Turning existing clip libraries into new narrated videos without manual editing.
Quick start
- 1
Download the latest version from GitHub Releases
- 2
Read the official user manual
Things to know
- Licensed under AGPL-3.0, a strong copyleft license that requires sharing modified source code when distributed or offered as a network service.
- Text-to-speech currently supports only EdgeTTS, with more voice APIs still planned.
Topics
FAQ
- What is short-video-factory?
- Open-source cross-platform desktop app that generates short marketing videos from text prompts and footage, with AI copywriting, TTS voiceover and automatic batch editing. Short Video Factory is a desktop application for producing product marketing and general-interest short videos with little manual editing. You provide a text prompt and a set of video clips, and the app generates the script with an AI model, converts it to speech, and assembles the clips with subtitles into a finished video.
- Is short-video-factory free to use? What license does it have?
- short-video-factory is open source under the AGPL-3.0 license. Check the license terms before using it in commercial products.
- Is short-video-factory still maintained?
- Actively maintained. The last commit to short-video-factory was on Oct 16, 2026.
- What can I use short-video-factory for?
- Producing product promotion videos for e-commerce listings. Making batches of general-interest short videos for social platforms. Turning existing clip libraries into new narrated videos without manual editing.
- How do I install short-video-factory?
- Download the latest version from GitHub Releases Read the official user manual
- Where can I get short-video-factory?
- The source code and installation instructions are on GitHub: https://github.com/YILS-LIN/short-video-factory
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Command-line tool that automatically cuts silent or inactive sections from video and audio, based mainly on loudness.
A local-first desktop writing assistant that proofreads, rewrites, and exports drafts without sending text to any server.
A self-improving AI agent that creates and refines skills from experience, runs on many model providers, and works through CLI and messaging apps.
Open-source Python framework for building real-time voice and multimodal AI agents, with pluggable speech, LLM, and transport services.
A bridge that lets AI assistants like Claude, Cursor or VS Code control the Unity Editor through the Model Context Protocol.