Skip to content
RepoQuarry

AutoClip zhouxiaoka/autoclip

Desktop app, Docker web UI and CLI/MCP that cut podcasts and interviews into platform-ready clips with captions, covers and post copy.

AutoClip at a glance

Checked 15 Oct 2026

AutoClip (v1.5.6, October 2026) takes a link or file, transcribes (creator captions, local Whisper/SenseVoice or cloud ASR), has an LLM rank highlights and renders up to 10 clips per platform with speaker-following vertical framing, captions, cover and post copy. Cutting and rendering run locally; analysis can use Ollama/LM Studio or a cloud LLM. MIT. Desktop for Windows x64 and Apple Silicon; Linux via Docker or CLI. Tuned for talking-head content; no shown virality score. Maintained by one person; README carries sponsor referral links.

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

How much of Opus Clip does it replace?

4 of 5 jobs. Covers clip picking, vertical framing, captions and publishing (Bilibili or Upload-Post account); no per-clip virality score shown.

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
No: Virality score per clip Not covered
Partial: 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? Confirmed: Yes, desktop app, Docker web UI or CLI; cutting and rendering always local Cutting, framing, and rendering run locally. github.com · README-EN.md#it-stays-on-your-computer ↗ 1d ago
Code licence Confirmed: MIT github.com · LICENSE ↗ 1d ago
Model weights licence Confirmed: No separate model weights; uses the Whisper/SenseVoice and LLM models you configure github.com · README-EN.md#model-setup ↗ 1d ago
Commercial use Confirmed: Yes, MIT code; terms of your chosen model providers apply The app is free and MIT-licensed. github.com · README-EN.md#faq ↗ 1d ago
Paid services needed? Partial: None required with Ollama / LM Studio and local Whisper; cloud LLM, cloud ASR, AI images and publishing services are optional Ollama / LM Studio need no cloud key but require suitable hardware. github.com · README-EN.md#faq ↗ 1d ago
Hardware Unknown: Not documented beyond needing extra memory and disk for local models Know the answer? —
Operating systems Confirmed: Desktop for Windows 10/11 x64 and macOS Apple Silicon; Intel Macs and Linux via Docker or CLI Intel Macs / Linux can use Docker or CLI. github.com · README-EN.md#quick-start ↗ 1d ago
Setup effort Confirmed: Easy, desktop installers (.dmg / -setup.exe) with Python and FFmpeg bundled; Docker or pip for CLI Python and FFmpeg are bundled. github.com · README-EN.md#desktop ↗ 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