OpenShorts mutonby/openshorts

Self-hosted Docker app that cuts long videos into captioned 9:16 shorts with AI moment picking, face-tracked reframing and social posting.

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

OpenShorts at a glance

Checked 15 Oct 2026

OpenShorts turns podcasts, webinars and streams into 9:16 clips: faster-whisper transcribes, an LLM (Gemini by default, or a local Ollama/OpenAI-compatible model) picks 3-15 moments, then MediaPipe/YOLOv8 reframes and burns in subtitles. Self-host with Docker (8GB+ RAM, CPU or NVIDIA GPU). Core is MIT; the cloud/ billing folder is source-available. A paid hosted version runs at openshorts.app. Also bundles AI UGC actor videos (paid fal.ai) and a YouTube title tool. A GitHub fork of Autocrop-vertical, but far diverged. No per-clip virality score.

Cite this pageRepoQuarry. “OpenShorts.” Checked 15 Oct 2026. https://repoquarry.dev/projects/openshorts

How much of Opus Clip does it replace?

4 of 5 jobs. Covers the core clip pipeline and scheduled posting (via Upload-Post); no per-clip virality score; feature parity not checked.

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 Partial replacement

Virality score per clip Not covered

Schedule and publish clips to social platforms Partial replacement

For virality score per clip, 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, self-hosted with Docker Compose; a paid hosted version also exists Self-hosting is genuinely free and always will be. github.com · openshorts#readme ↗ 1d ago

Code licence MIT for the core app; the cloud/ folder (billing, hosted infrastructure) is source-available under a commercial licence MIT License for the core application — OpenShorts is yours to use, modify, and scale. github.com · openshorts#license ↗ 1d ago

Model weights licence No separate model weights; downloads third-party models (faster-whisper, YOLOv8, MediaPipe) and calls the LLM you choose github.com · openshorts#tech-stack ↗ 1d ago

Commercial use Yes for the MIT core; the cloud/ billing folder may not be resold as a hosted service. Licences of bundled models (e.g. ultralytics YOLOv8) not checked you can't offer it to third parties as a paid/hosted service. Self-hosting the core app never requires this directory. github.com · openshorts#license ↗ 1d ago

Paid services needed? Clipping can run with a local LLM and no paid key; Gemini is the default and is needed for auto-layout and silent videos; posting, dubbing and AI actors use paid APIs Point it at any OpenAI-compatible server instead and the whole pipeline stays on your box github.com · openshorts#6-run-without-a-google-key-local-llm-optional ↗ 1d ago

Hardware 8GB+ RAM; CPU works (5-8 min per 8-min video); optional NVIDIA GPU, 8GB VRAM enough for large-v3-turbo Docker, 8GB+ RAM, model downloads github.com · openshorts#readme ↗ 1d ago

Operating systems Runs in Docker; Linux and Windows (Docker Desktop with WSL2) are documented; macOS not mentioned On Windows use Docker Desktop with the WSL2 backend and the Windows NVIDIA driver github.com · openshorts#5-gpu-acceleration-optional-nvidia ↗ 1d ago

Setup effort Medium, docker compose up --build, then enter API keys in the dashboard docker compose up --build github.com · openshorts#getting-started ↗ 1d ago