Skip to content
RepoQuarry

HotClip xixihhhh/hotclip

Desktop app that cuts long videos and livestream replays into 9:16 shorts with AI highlight picks, virality scores, auto-reframe and word-level captions.

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

HotClip at a glance

Checked 16 Oct 2026

HotClip (v0.32.1, October 2026) is an Electron desktop app that transcribes locally, has an LLM pick highlights with a virality score and reasoning, then exports 9:16 clips with face-aware reframing, burned-in word-level captions, covers and post copy. Strong on Chinese video and livestream chat logs (Bilibili, Douyin). The highlight LLM is a cloud API with your key by default, or local Ollama. Code is AGPL-3.0. It builds per-platform folders but does not post to social accounts itself. Linux build is experimental; macOS is Apple Silicon only.

Cite this pageRepoQuarry. “HotClip.” Checked 16 Oct 2026. https://repoquarry.dev/projects/hotclip

How much of Opus Clip does it replace?

4 of 5 jobs. Covers highlight picking, scoring, reframing and captions locally; no direct posting or scheduling to social accounts.

Partial: AI picks highlight clips from a long video Partial replacement
Partial: Auto-reframe to vertical 9:16 (speaker or face tracking) Partial replacement
Partial: Animated burned-in captions on clips Partial replacement
Partial: Virality score per clip Partial replacement
No: Schedule and publish clips to social platforms Not covered

For 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? Confirmed: Yes, desktop app; transcription, captions, cutting and export are local, and the highlight LLM can be local Ollama Yes — transcription, captions, cutting and export all run on your machine. github.com · README.en.md#faq ↗ 1d ago
Code licence Partial: AGPL-3.0-only (copyleft) github.com · LICENSE ↗ 1d ago
Model weights licence Partial: SenseVoiceSmall's official model card links the custom FunASR Model License, with attribution, model-name retention and other restrictions; do not assume the code licence covers all selectable ASR or LLM weights You are free to use, copy, modify, and share [FunASR Software] under the terms of this agreement. github.com · MODEL_LICENSE ↗ today
Commercial use Partial: AGPL-3.0 code allows it with conditions; model licences are not stated; meant for your own or authorised content github.com · README.en.md#license--boundaries ↗ 1d ago
Paid services needed? Partial: None required with local Ollama; cloud LLM (the default), ElevenLabs transcription, AI covers and AI music are optional and billed to your key Optional cloud LLMs bill your own key; a local Ollama model makes it fully free and offline. github.com · README.en.md#faq ↗ 1d ago
Hardware Confirmed: No GPU needed; local ASR runs on CPU (a local Ollama LLM needs more); RAM not stated No. The local ASR models are int8-quantized and run fine on CPU github.com · README.en.md#faq ↗ 1d ago
Operating systems Confirmed: Windows x64, macOS Apple Silicon only, Linux AppImage (experimental) Linux (experimental) | `HotClip-x.y.z-linux-x64.AppImage` github.com · README.en.md#%EF%B8%8F-download ↗ 1d ago
Setup effort Confirmed: Easy, installer or portable zip (unsigned builds) No Python, no Docker, no command line, no account — a real desktop app you double-click. github.com · README.en.md#%EF%B8%8F-download ↗ 1d ago

Get the weekly top 5 and what’s new, every Monday

We’ll email you once a week. Unsubscribe any time. We never share your email.

Cookie preferences

Choose what we may store in your browser. You can change this any time from Cookie settings in the footer.

Essential

Security, and remembering this choice. rq-consent · 12 months

Always on