OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

AI Youtube Shorts Generator

AI Youtube Shorts Generator is an open-source Python application that processes long-form YouTube videos into short clips using speech transcription, LLM-based highlight selection and automatic cropping. It offers API and local processing modes, plus command-line and Python-library interfaces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Youtube Shorts Generator — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a self-hosted Python workflow for finding candidate clips in long YouTube videos and reframing them, or when you want to integrate the clipping process into a script or application.

Who it is for

  • Creators who want to extract short clips from long-form YouTube videos.
  • Agencies processing video into short-form content.
  • Developers building or adapting a video-clipping workflow.

Documented uses

  • Transcribe speech in a YouTube video.
  • Identify and rank candidate highlight segments.
  • Crop selected video into vertical or other aspect ratios.
  • Export structured results as JSON for downstream automation.
Before you choose

Requirements & limits

The project is public and identifies an MIT license. Self-hosted setup requires Python 3.10 or later; API mode requires a MuAPI key, while local mode requires ffmpeg and an OpenAI or Gemini key for highlight ranking.

  • API mode uses MuAPI for download, transcription, highlight ranking and clipping; local mode uses yt-dlp, faster-whisper and ffmpeg or OpenCV.
  • Local mode still sends the highlight-ranking step to an OpenAI or Gemini LLM API.
  • Local transcription supports faster-whisper on CPU or CUDA.
  • The project documents a CLI, Python-library use and JSON output for automation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the self-hosted project

Prepare the Python application and configure credentials for API mode or local processing.

Before you start

  • Python 3.10 or later
  • For API mode: a MuAPI key
  • For local mode: ffmpeg on PATH and an OpenAI or Gemini API key

Steps

  1. Clone the repository and enter its directory.

  2. Create and activate a Python virtual environment.

  3. Install the requirements file; for local mode, also install the local requirements file.

  4. Create a .env file and set the credentials for the selected mode.

Expected outcome

The project environment and mode-specific credentials are prepared for the next workflow stage.

Guide limitations

  • These instructions cover setup, not running a video through the application.
  • Local mode still uses a remote LLM for highlight selection.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
Anil-matcha/AI-Youtube-Shorts-Generator · Official homepage title · retained in its source language
How we review sourcesSuggest a correction