AutoShorts (JayWebtech) JayWebtech/autoshorts

Tauri desktop app that transcribes a long recording, ranks viral moments with an LLM and center-crops them into vertical 9:16 clips.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

AutoShorts (JayWebtech) at a glance

Checked 15 Oct 2026

AutoShorts (v0.1.5, July 2026) is a Tauri/React/Rust desktop app for macOS, Windows and Linux. It transcribes with Deepgram or local Whisper, ranks moments with DeepSeek, Claude or a local Ollama model, and center-crops clips to 9:16 with FFmpeg. The repo has no licence file, so by default you may not reuse the code. Cropping is a plain center crop, not face or speaker tracking; the README says local models are not recommended for moment detection. No social publishing.

Cite this pageRepoQuarry. “AutoShorts (JayWebtech).” Checked 15 Oct 2026. https://repoquarry.dev/projects/autoshorts

How much of Opus Clip does it replace?

2 of 5 jobs. LLM moment ranking plus a fixed center crop to 9:16; no speaker tracking, virality score UI or social publishing.

AI picks highlight clips from a long video Partial replacement

Auto-reframe to vertical 9:16 (speaker or face tracking) Partial replacement

Animated burned-in captions on clips Not covered

Virality score per clip Not covered

Schedule and publish clips to social platforms Not covered

For animated burned-in captions on clips, virality score per clip, schedule and publish clips to social platforms, see other Opus Clip alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, desktop app; fully offline mode with Ollama and local Whisper Option A: Fully Offline (Ollama + Whisper) github.com · autoshorts#readme ↗ 1d ago

Model weights licence No bundled weights; uses the Ollama, Whisper or cloud models you choose github.com · autoshorts#readme ↗ 1d ago

Commercial use No licence granted for the code, so reuse or redistribution is not permitted by default github.com · autoshorts ↗ 1d ago

Paid services needed? Not required (Ollama + local Whisper); the recommended setup uses paid Deepgram and DeepSeek or Claude APIs local models are generally not recommended for viral moment detection github.com · autoshorts#readme ↗ 1d ago

Hardware Not documented; FFmpeg must be on PATH Know the answer? —

Operating systems macOS (Apple Silicon and Intel), Windows, Linux (.deb, .rpm, AppImage) Select the .msi (installer) or .exe (portable executable) package. github.com · autoshorts#readme ↗ 1d ago

Setup effort Easy; unsigned installers from GitHub Releases plus FFmpeg on PATH Download the correct package matching your system from the latest GitHub Releases. github.com · autoshorts#installation-guide-for-users ↗ 1d ago