YT Short Clipper jipraks/yt-short-clipper

Windows desktop app that turns a YouTube video into 9:16 clips with LLM highlight picking, face-tracked reframing and word-by-word captions.

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

YT Short Clipper at a glance

Checked 15 Oct 2026

YT Short Clipper v2 (v2.0.7-beta, September 2026) is a Tauri desktop app for Windows only. You paste a YouTube URL, an LLM reads the video's own subtitle track and proposes 58-120 second highlights, and each clip is reframed to 9:16 (MediaPipe face tracking or centred) with burned-in captions. Needs your own YouTube cookies.txt. Works with any OpenAI-compatible endpoint, including local Ollama. MIT. No virality score, no local file input documented, and it needs a source with subtitles. Official builds send anonymous usage events to Google Analytics.

Cite this pageRepoQuarry. “YT Short Clipper.” Checked 15 Oct 2026. https://repoquarry.dev/projects/yt-short-clipper

How much of Opus Clip does it replace?

4 of 5 jobs. YouTube URLs only, Windows only, beta; captions come from YouTube's subtitle track; publishing only through the third-party Repliz service.

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, Windows desktop app; the LLM step can be local (Ollama, vLLM) or a cloud API a Custom/Local option for vLLM, Ollama, or similar. github.com · yt-short-clipper#readme ↗ 1d ago

Code licence MIT github.com · LICENSE ↗ 1d ago

Model weights licence No bundled LLM weights; uses the provider you configure (MediaPipe for face tracking) github.com · yt-short-clipper#readme ↗ 1d ago

Commercial use Yes, MIT code; you must have rights to the YouTube videos you re-cut Only use it on content you own or are otherwise licensed to reuse github.com · yt-short-clipper#legal ↗ 1d ago

Paid services needed? Not required with a local Ollama/vLLM model; cloud LLM APIs, the in-app AI wallet and Repliz upload are optional paid extras Top up with QRIS from inside the app and the balance shows in the sidebar. github.com · yt-short-clipper#ai-providers ↗ 1d ago

Hardware Not documented Know the answer? —

Operating systems Windows 10/11 only; not ready for macOS or Linux Nothing is macOS/Linux-ready today. github.com · yt-short-clipper#readme ↗ 1d ago

Setup effort Easy, portable zip from GitHub Releases; building from source needs Node, Rust and Python YTShortClipperV2_2.0.7-beta_x64_portable.zip github.com · releases ↗ 1d ago