JayWebtech/autoshorts

AutoShorts is a local-first desktop application for turning long-form video or audio recordings into high-impact, vertical short-form clip candidates (9:16 portrait) with AI-powered viral moment ranking.

What it solves

AutoShorts is a desktop application designed to help content creators turn long-form video or audio recordings into high-impact, vertical short-form clips (9:16 portrait) by automatically identifying and ranking the most "viral" moments of a recording.

How it works

The application uses an automated pipeline to process media: it imports the file, extracts audio, and transcribes the content using either Deepgram (cloud) or OpenAI Whisper (local). It then leverages LLMs—such as DeepSeek, Claude, or local models via Ollama—to analyze the transcript and detect viral moments and hooks. Finally, it uses native ffmpeg integration to automatically center-crop landscape videos into vertical portrait clips.

Who it’s for

Content creators and podcasters who need to quickly extract the most engaging segments from long videos or audio recordings for social media platforms.

Highlights

  • Multi-LLM Support: Flexible choice between DeepSeek, Claude, and local Ollama models for moment detection.
  • Automated Pipeline: A single chain that handles everything from transcription to moment ranking.
  • Local-First Design: Uses a local SQLite database to store transcripts, project data, and rendering information.
  • Native Cropping: Automatic landscape-to-portrait conversion using FFmpeg.
  • Hybrid AI Workflow: Supports both fully offline processing (Ollama + Whisper) and high-performance cloud APIs.

Related

  • Project
    xixihhhh/hotclip

    An open-source AI tool that automatically converts long videos and live stream replays into viral vertical short-form videos using local transcription and highlight detection.

  • Project
    Anil-matcha/AI-Youtube-Shorts-Generator

    An open-source AI tool that converts long-form YouTube videos into viral vertical shorts by using LLMs for highlight detection and Whisper for transcription.

  • Project
    bridge-mind/bridgeclip

    BridgeClip is an open‑source desktop app that uses LLMs (via OpenRouter) to automatically find, caption, and export short clips from long videos, with local video rendering and optional edit/review tools.

  • Project
    RafaelGodoyEbert/ViralCutter

    An open-source, local AI tool that transforms long YouTube videos into viral short-form clips with automatic cropping, dynamic captions, and face tracking.

  • Project
    zhouxiaoka/autoclip

    An open-source tool that automatically converts long videos into short-form clips for social media, generating the video, cover, and captions using AI.