Concat: a free CapCut that runs offline

The free, open-source video editor from the reel. Auto captions, text to speech, voice cloning, background removal, keyframes, effects and 4K export, all on your own computer. No watermark, no account, no subscription, nothing uploads.

CostFree and open source (AGPL-3.0). No watermark, no account, no paid tier.

DoesMulti-track video editing with auto captions (local Whisper), text to speech and voice cloning, background removal, keyframes, 100 effects, filters and transitions, titles, voice cleanup and export up to 4K 60 (H.264, HEVC, AV1).

NeedsWindows (64-bit Intel/AMD), macOS 12+ (Apple chip or Intel), Linux, or Android 8+. iPhone/iPad only by sideloading. 4 GB RAM minimum, 16 GB recommended for 4K and the bigger caption models.

Proof9.3k stars on GitHub in under two months

Checked on 19 Oct 2026. Tools change fast, so the official page always wins if it says something different.

What you need first

1A computer or Android phoneWindows, Mac or Linux for the full desktop app. Android works too. iPhone needs sideloading, so it's not for most people yet.

2Some free disk spaceAbout 500 MB for the app and the smallest caption model. All the optional AI models together are about 3.4 GB. They download once and then work offline.

Step by step

Download it

Open the official website (link below) and click Download: it picks the right build for your computer. Or open Releases on the GitHub page and pick it yourself: Mac macos-arm64.dmg (Apple chip) or macos-x86_64.dmg (Intel), Windows windows-x86_64-setup.exe, Linux .deb, .rpm or .AppImage, Android .apk.

Tip: Only download from the official website or the GitHub Releases page.

Open it the first time

The builds aren't code-signed yet, so your computer will warn you. Windows: on the SmartScreen box click More info → Run anyway. Mac: drag the app into Applications, then if macOS refuses to open it, paste this in Terminal once: xattr -dr com.apple.quarantine /Applications/Concat.app

Get the AI models

Go to Settings and download the models you want: auto captions (Whisper Tiny, Base or Small), voices, voice cloning and cutout. Start with a small caption model, they're quicker.

Make your first edit

Drop your clips onto the timeline, cut and trim, then add auto captions. For a voiceover, type the text and pick a voice, or clone your own voice from a few seconds of a recording.

Export

Export up to 4K 60 in H.264, HEVC or AV1. For Reels, TikTok and Shorts, set the canvas to vertical (9:16) before you export.

Learn this with me

LIVE · THU 15 OCT

Live AI Masterclass

8 ways I make money with AI, built live step by step. Zero experience, no code, any age.

Thu 15 Oct · 6pm UK · 1pm ET
New date coming soon. See what you'll learn and the next date →
2 hours live + the replay
$150 one time · only 10 seats

Join the masterclass →

MEMBERS

The Unnerd AI Club

Not a course. A step-by-step system to make money with AI: pick one money path and follow every step.

52 live classes a year
Q&A 7 days a week + 1:1 calls with me
$100/month · cancel any time

Join the club →

The catch

It's in beta. It works, but it still has rough edges. Keep a backup of important projects and report bugs on GitHub.
Unsigned builds. Windows and Mac show a warning the first time you open it (steps above).
Your computer does the work. Smooth 4K and the bigger caption models want 16 GB of RAM and a decent GPU. Older laptops are fine for 1080p.
Voice cloning: only clone your own voice or one you have permission to use.
iPhone is sideload-only for now, so most iPhone users should edit on a computer.

Official links

The tool on GitHub (official) ↗Official website and download ↗

Want to go further?

I show a new AI tool every week, and how to make money or save hours with it. No tech background needed.

Join the live masterclass Join the club

More free tools →

Unnerd AI · I'm not linked to this tool or its makers, I just think it's useful.