The gist

Short Video Maker is an open-source tool for automating the creation of short-form video content. Developed by the AI Agents A-Z YouTube Channel, it solves the problem of producing engaging social media videos without needing powerful GPUs or expensive third-party APIs. It combines text-to-speech, automated captions, stock footage, and background music to turn simple text inputs into finished videos for platforms like YouTube Shorts, Instagram Reels, and TikTok.

What it does

Generates complete short videos from text prompts.
Converts text into an English-language voiceover using text-to-speech.
Automatically generates and styles captions from the audio track.
Searches Pexels and adds relevant stock videos as background footage.
Adds background music based on a selected genre or mood.
Exposes a REST API for programmatic video generation and management.

How it works

Users submit text scenes and search terms via a REST API. The tool converts text to speech, generates captions, fetches background videos from Pexels, and composes all elements into a final video file using Remotion. It is an open-source project intended for self-hosting via Docker, which is the recommended method. A free Pexels API key is required for operation, and the output is a downloadable MP4 video file.

Best for

This tool is ideal for developers and technical content creators who need to programmatically generate faceless short-form videos for social media platforms.

Watch out for

The tool currently only supports English voiceovers. It cannot use custom images or video clips as inputs, relying solely on Pexels for background footage. Windows is not officially supported for non-Docker installations.