Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

autoclip

autoclip: An open-source AI desktop tool that turns long videos into short clips, subtitles, covers, and publishing copy.

What problem it solves

Long-form podcasts, interviews, and courses require extensive manual work to identify highlights, reframe footage, add subtitles, prepare covers, and write publishing copy. This project automates those steps from a source link while retaining local editing and rendering for users who need to adjust the result.

Key features

  • Platform-aware clip generation — Choose a target platform and generate clips according to its aspect-ratio and duration requirements. The tool can produce up to 10 qualified clips per platform, with additional candidates available on request.

    Source: README

  • Packaged publishing assets — Each clip is prepared with a cover, title, description, topics, and a ZIP publishing package, reducing the additional work needed to publish the result.

    Source: README

  • Automated framing and subtitles — The default layouts vary by platform, while framing follows the active speaker and preserves the complete scene when no person is present. Subtitles and publishing-copy language follow the selected platform.

    Source: README

  • Local editing and model choice — Editing, framing, and rendering run on the user's computer. Users can choose cloud or local analysis and can select author subtitles, local transcription, or configured cloud transcription.

    Source: README, docs/PRIVACY.md

  • Desktop, Docker, CLI, and MCP access — The desktop application shares its one-click production workflow with CLI and MCP interfaces. Docker supports self-hosted Web and Linux deployments, while CLI and MCP support batch processing and Agent integration.

    Source: README

Quick start

Copied verbatim from the project's README.

# 一行安装
uvx autoclip-mcp
npx skills add zhouxiaoka/autoclip
autoclip --version
autoclip produce talk.mp4 --srt talk.srt --platform douyin --portrait-style podcast --json
autoclip outputs PROJECT_ID --export-kits

Who it may suit

This may suit creators repurposing podcasts, interviews, courses, and spoken-word footage for short-form social platforms, as well as developers integrating automated clipping through CLI or MCP.

Topics to discuss

  • Which platform-specific layouts and publishing requirements should receive more community testing?

  • How should clip selection, speaker framing, and subtitle quality be evaluated?

  • What local model and transcription workflows would be most useful for the community?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/zhouxiaoka/autoclip#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/zhouxiaoka/autoclip

Comments

…