#77th of 56 in Image and videoFor image, video and design, video and animation

autoclip

Turns a video link into short clips with covers and captions

Stars
10.3k
License
MIT
Last commit
Nov 2026
Last release
Nov 2026
Language
Python
Stars, last 29 weeks+5,653
20 Apr 2026: 4,650 stars27 Apr 2026: 5,010 stars4 May 2026: 5,085 stars11 May 2026: 5,162 stars18 May 2026: 5,249 stars25 May 2026: 5,403 stars1 Jun 2026: 5,515 stars8 Jun 2026: 5,579 stars15 Jun 2026: 5,651 stars22 Jun 2026: 5,709 stars29 Jun 2026: 5,824 stars6 Jul 2026: 5,955 stars13 Jul 2026: 6,041 stars20 Jul 2026: 6,173 stars27 Jul 2026: 6,239 stars3 Aug 2026: 6,299 stars10 Aug 2026: 6,346 stars17 Aug 2026: 6,409 stars24 Aug 2026: 7,016 stars31 Aug 2026: 7,164 stars7 Sept 2026: 7,264 stars14 Sept 2026: 7,350 stars21 Sept 2026: 8,498 stars28 Sept 2026: 9,052 stars5 Oct 2026: 9,216 stars12 Oct 2026: 9,429 stars19 Oct 2026: 9,641 stars26 Oct 2026: 9,837 stars2 Nov 2026: 10,015 stars9 Nov 2026: 10,303 stars

4,650 on 20 Apr 202610,303 on 9 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

AutoClip takes a video URL or local file, transcribes it (author subtitles, local Whisper/SenseVoice, or cloud ASR), and has an LLM pick up to 10 clips per target platform. It renders them locally with FFmpeg, following the speaker in portrait layouts, and adds covers, titles and publish copy. It ships as a desktop app, a Docker web service, and a CLI/MCP server.

Who it is for: Creators repurposing long interviews and podcasts into short-form clips

Ranked among open-source alternatives to Midjourney (#7 of 10).

Strengths

  • Editing and rendering run locally; cloud is used only for chosen analysis, transcription or image steps
  • Same pipeline from desktop, CLI and MCP server, so agents can drive it
  • Works with Ollama and LM Studio for local analysis, plus OpenAI-compatible APIs
  • README gives measured runs: 1h43m source to 10 clips in 7.5 minutes on Apple Silicon

Weaknesses

  • Desktop installers only for macOS Apple Silicon and Windows x64; Intel Mac and Linux need Docker or CLI
  • Tuned for interviews, podcasts and talking-head video; screen recordings need vision models and manual checks
  • Branded end card is on by default and must be turned off in settings
  • Cloud analysis and transcription are billed by the provider and need your own API keys

What it needs

  • GPU optional
  • Docker + Compose
  • Needs FFmpeg, Python 3.10+, Docker Compose v2, Ollama or LM Studio (optional), Cloud LLM API key (optional)
  • Models: OpenAI-compatible APIs, Ollama, LM Studio, Whisper, SenseVoice
  • port 3000

What changed

From the release notes. No flag means the note does not say so, not that the upgrade is safe.

Quick answers

Is autoclip open source?

Yes. Its code is on GitHub under the MIT license.

Can you run autoclip with Docker?

Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.

Does autoclip need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Also in Image and video

See all 56
Also in Image and video
RankProjectScore
1frigateLocal NVR with realtime object detection for IP cameras37.4k starsMIT92 out of 100
2MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles142.4k stars+12,729 (+9.8%) in 30 daysMIT88 out of 100
3toonflow-appInfinite-canvas tool for AI short drama and comic video production21.4k stars+4,197 (+24%) in 30 daysMIT86 out of 100
#4ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows146.3k stars+9,609 (+7.0%) in 30 daysGPL-3.085 out of 100
#5InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows29.1k stars+545 (+1.9%) in 30 daysApache-2.085 out of 100