Verified project record

zhouxiaoka/autoclip

AutoClip turns a single video link into up to 10 short clips per platform, complete with covers, titles, descriptions, hashtags, and a ZIP publishing kit adapted to Douyin, Xiaohongshu, TikTok, Reels, Shorts, Bilibili, and YouTube. Cutting, speaker framing, and rendering run on your own computer, while analysis can use a cloud API key or a local Ollama/LM Studio model.

Project overview

It automates clip generation with covers and per-platform publishing copy from a single video link, while cutting, speaker framing, and rendering run on the user's own computer — a workflow that reduces manual work when repurposing podcasts, interviews, and courses.

Project type: MCP · Video
Use cases: Documents & Office · Translation & Subtitles · Video Creation
Deployment: Refer to project documentation
License: MIT

Best for

Creators who need to convert interviews, podcasts, courses, and other talking-head videos into short clips with subtitles, covers, and publishing copy for Douyin, Xiaohongshu, TikTok, Reels, Shorts, Bilibili, or YouTube.
Developers who want the clip pipeline through CLI/MCP for batch processing or agent integration, or as a Docker web service.

Key capabilities

Given a video link and target platform, automatically generates up to 10 qualified clips per platform, each with a cover, title, description, hashtags, and a ZIP publishing kit.
Cutting, speaker framing, and rendering run on the user's own computer. Subtitles can come from author-supplied subtitles, local Whisper/SenseVoice, or a configured cloud transcription service.
The same one-click clip pipeline is available as a desktop app (macOS Apple Silicon / Windows x64), a Docker web service, and CLI/MCP entry points for batch processing and agent integration.

Limitations and risks

Interviews, podcasts, courses, and talking-head content are the main validated scenarios; game recordings with little speech may need image recognition and manual checks.
Cloud analysis, transcription, and AI image generation are billed by the chosen provider using the user's own credentials; GPU requirements are not documented.

Getting started

Download and install the desktop version (.dmg / -setup.exe), open settings to choose a provider, enter an API key, and select an available analysis model, then paste a link and pick a platform, preview the generated clips, and download the publishing package.

Evidence and sources

GitHub project description
README
README
README
README

Source updated at: 2026-10-22T18:43:04Z

Open original GitHub project