short-video-maker
277
This project is an open-source tool for generating short-form videos from simple text inputs. It combines text-to-speech, automatic captions, and background media to create engaging video content. It supports both REST API and MCP server functionalities for flexible integration.
Can I use other languages?
Unfortunately, it’s not possible at the moment. Kokoro-js only supports English.
Can I pass in images and videos and can it stitch it together?
No, this feature is not supported.
Should I run the project with npm or docker?
Docker is the recommended way to run the project.
How much GPU is being used for the video generation?
Not a lot - only whisper.cpp can be accelerated. Remotion is CPU-heavy, and Kokoro-js runs on the CPU.
Is there a UI that I can use to generate the videos?
No, there is no UI available yet.