AutoClip

by Kris KAppMake video or audio

Turns a long interview, podcast or course video into captioned short clips with post copy

The problem it solves

Your two-hour podcast has five great moments, and finding, cutting and captioning each one for Shorts eats your whole weekend.

For PodcastersCourse creatorsCreators reusing interviews

Before: You scrub the timeline for good moments, reframe each one for vertical video, add captions and write post text by hand.
After: You paste a link or import a file, pick a platform, and get clips with captions, a cover, a title, a description and hashtags.

Stars: ★ 9.9k
License: MIT
Cost: Usage-based
Platforms: Mac · Win · Linux
Runs: Local · Self-hosted

Screenshots

From the project's own repository.

The export dialog for choosing a platform, burned-in captions and a title card — Image: Kris K (MIT). Original file

Overview

AutoClip is a desktop app that cuts long videos into short clips for social platforms. You paste a video link or import a file and pick a platform such as Douyin, Xiaohongshu, TikTok, Reels, YouTube Shorts, Bilibili or YouTube; it picks the moments, cuts and frames them, adds captions, and gives each clip a cover, title, description and hashtags. Cutting and rendering run on your computer, and the analysis uses an AI model you connect. It suits podcasters, course makers and creators reusing interviews.

It returns finished clips with a cover and post text in one pass, and you can still open each clip in its editor to adjust it.

Try these first

Start with the first one: it is a small task you can check easily.

Import a captioned interview you own, choose YouTube Shorts, and check the first clip's captions and ending.First try · uses model credits
Paste a Bilibili or YouTube link to your own talk and choose Xiaohongshu with the interview layout.uses model credits
Open a clip in the editor, change its title template and turn off the title card, then export it again.
In Settings, connect Ollama or LM Studio and run the same video with a local model.

Example prompts written by Agent Flows Hub.

Features

From the creator's documentation.

Feature	What it does	Runs
Link or file import	Paste a Bilibili or YouTube link, or import a video file	Your computer
Platform presets	Frame and length rules for Douyin, Xiaohongshu, TikTok, Reels, Shorts, Bilibili and YouTube	Your computer
Clip picking	An AI model ranks moments and up to 10 clips per platform are rendered	Your model provider
Publish kit	Each clip comes with a cover, title, description, hashtags and a ZIP kit	Your computer
Editor	Adjust title templates, captions, translation and sound before export	Your computer
Publishing	Post directly after you connect a Bilibili or Upload-Post account	Your accounts

Good to know

You recorded or found a long interview and want several short vertical clips for one platform. AutoClip picks the moments, frames the speaker, burns in captions and writes a cover, title, description and hashtags for each clip.

Limits

Cloud analysis sends captions and post text to your model provider, and cloud transcription sends audio. Local models through Ollama or LM Studio avoid that but need suitable hardware.
A brand outro is added by default; turn it off in Settings. Interviews, podcasts, courses and talking-head videos are the main use; low-dialogue footage needs an image-capable model.
The desktop builds may be unsigned, so macOS or Windows can block the first launch. The installation guide says to check the download came from the project's Releases page and follow that release's notes.

Notes by Agent Flows Hub (original project name: AutoClip), written from the creator's documentation, not from running it ourselves. AutoClip README (English) · AutoClip installation guide

Stuck setting it up?

Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.

Get help

How to start

Get the appDownload it from the official page, or paste the install request into an AI agent you already use.macOSDownload the installerWindowsDownload the installerLinuxgit clone https://github.com/zhouxiaoka/autoclip.git cd autoclip cp env.example .env mkdir -p data logs uploads docker compose up -d --build
Open itFollow the first-run steps in the app.
Give it a first taskImport a captioned interview you have the rights to and pick one platform. Check the first clip's captions, framing and whether the clip ends on a complete thought.

Steps follow the creator's instructions. The request tells your agent to read them first and wait for your OK.

Before you start

A computer with macOS, Windows or Linux.
An API key for a cloud AI model, or a local model in Ollama or LM Studio
A Mac with Apple Silicon or Windows 10 or 11 (x64); Docker on Linux or Intel Macs
Videos you have the right to cut and repost
Pay per use. The AI service it calls charges for what you use.

Details

Made by: Kris K
License: MIT Terms
Platforms: macOS, Windows, Linux
Runs on: Your computer, Self-hosted server

View source Official docs Report a problem

For AI agents

This page as a Markdown install brief:

/en/library/autoclip/install.md

Other apps

Buzz Turns recordings, videos and YouTube links into text and subtitles on your own computer
Chat UI Gives you your own HuggingChat-style chat page for the AI models you choose
ChatGPT Desktop Brings ChatGPT chat, Work tasks and the Codex coding agent to your desktop
ChatGPT Exporter Saves your ChatGPT conversations as Markdown, HTML, JSON, text or a screenshot
ChatGPT Telegram Workers Puts your own AI chat bot in Telegram, deployed to Cloudflare with one button
ChatGPTBox Adds an AI chat box to any web page to summarise, translate or rewrite what you read

See all 113 apps

GitHub