Picture published by the creator on GitHub.
Concat: Edit videos with auto captions and AI voices offline
Added · Updated
Made by Jareer A.
View profile on GitHub (opens in a new tab)Cut videos and add auto captions, voices and effects on your own computer.
For people making TikToks, Reels, Shorts and YouTube videos.
What it does
Concat is a video editor that runs entirely on your computer using a native Rust engine with GPU rendering. AI models for captions (local Whisper), text-to-speech and background removal download once, then work offline, so your footage never leaves your disk.
How to use it
Download the build for your system from the download link in the project's documentation, install it, drop in footage and start cutting. Developers and AI agents can also control it through a built-in MCP server (a way for AI assistants to use tools) or a JSON-RPC scripting API.
Common use cases
- Drop in a talking-head clip, pick a Whisper model size, and get styled captions placed on the timeline.
- Record a few seconds of your voice and generate a voiceover in that voice for a tutorial video.
- Trim a podcast recording into short clips, clean up the voice with one switch, then export up to 4K 60.
Can I use this?
Requirements Install the app from the download page or GitHub releases. On first use, download the caption, voice and cutout models from Settings. On Windows, an unsigned build may need More info, then Run anyway.
Caveat Concat is in beta: it works but still has edges, and Windows ARM builds are paused. Specific RAM or GPU requirements are not documented.
Worth knowing Beta software that still has rough edges; Windows ARM builds are paused, and unsigned builds may trigger a system warning before opening. Licensed under GNU Affero General Public License v3.0.
Why it's here
- 15,553 people have starred it on GitHub.
Numbers as of 8 November 2026, from BuildTube’s latest daily refresh.
Behind it
View setup guideBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is Concat?
- Concat is a video editor that runs entirely on your computer using a native Rust engine with GPU rendering.
- What can I use Concat for?
- Drop in a talking-head clip, pick a Whisper model size, and get styled captions placed on the timeline; Record a few seconds of your voice and generate a voiceover in that voice for a tutorial video; Trim a podcast recording into short clips, clean up the voice with one switch, then export up to 4K 60
- Can I run Concat on my computer?
- It installs as a desktop app on your own computer. On Windows, an unsigned build may need More info, then Run anyway. Concat is in beta: it works but still has edges, and Windows ARM builds are paused. Specific RAM or GPU requirements are not documented.
- What do I need to use Concat?
- A macOS, Windows, Linux or Android device. AI models for captions, voices and cutout download once from Settings.
- What license does Concat use?
- Licensed under GNU Affero General Public License v3.0.
More from this week
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
- Auto-Ontology Give AI agents checked business meanings for your database
Help AI agents answer questions about company databases using reviewed definitions and SQL, with each answer showing its steps.
- Spec Kit Turn a written spec into plans, tasks and code
Spec Kit gives your AI coding agent a step-by-step process to build a feature, fix a bug or assess an idea.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/gh-jub0t-concat/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/gh-jub0t-concat/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="Concat on BuildTube"></iframe>