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

AutoShorts AI

AutoShorts AI is a Python application that generates short-form videos from a topic by combining Google Gemini scriptwriting, Edge-TTS narration, Pexels stock footage and FFmpeg editing.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AutoShorts AI — 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 local Python workflow to automate scripting, narration, stock-footage sourcing and assembly for short-form videos.

Who it is for

  • Creators producing faceless YouTube Shorts or TikTok videos.
  • People building a repeatable topic-to-video workflow with automated narration and stock-footage editing.

Documented uses

  • Turn a topic into a structured, multi-scene script.
  • Generate narration and find portrait-format stock footage for scenes.
  • Assemble paired visuals, voiceover and transitions into a short video.
  • Include a custom avatar or mascot video in a middle scene.
Before you choose

Requirements & limits

The project is a public GitHub repository with an MIT license. Its README documents local setup and requires Gemini and Pexels API keys.

  • The scriptwriter uses Google Gemini 2.0 Flash by default, with an optional GEMINI_MODEL override.
  • Pexels supplies paired portrait-format stock clips; the README describes reusing the first clip if a second is unavailable.
  • The voiceover stage uses Edge-TTS, and the editor uses FFmpeg for trimming, transitions and rendering.
  • A user-provided avatar is optional to the setup but required for the described avatar-injection element.

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

Generate a short video from a topic

Run the documented pipeline to create a short video from a subject.

Before you start

  • Python 3.10 or later and FFmpeg installed and available on the system PATH.
  • Google Gemini and Pexels API keys.
  • Repository dependencies installed with pip from requirements.txt.
  • An avatar video at assets/avatar/avatars.mp4 if using avatar injection.

Steps

  1. Clone the repository and install its requirements with pip install -r requirements.txt.

  2. Create the assets/avatar folder and place the avatar video there as avatars.mp4 if desired.

  3. Copy .env.example to .env and set GEMINI_API_KEY and PEXELS_API_KEY; GEMINI_MODEL is optional.

  4. Run python main.py and enter a topic when prompted.

Expected outcome

The README identifies assets/final/final_short.mp4 as the output location.

Guide limitations

  • The workflow depends on Gemini for scripts and Pexels for stock footage, so both API keys are required.
  • The guide documents a local command-line workflow and does not establish a public API or hosted service.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
SaarD00/AI-Youtube-Shorts-Generator · Official homepage title · retained in its source language
How we review sourcesSuggest a correction