# AI use cases for Concat (jub0t/Concat)

Repo: [jub0t/Concat](https://github.com/jub0t/Concat) | Use cases: 3 | Page: https://dedupedai.com/use-cases/jub0t-concat/

Concat is a free, open-source video editor and CapCut alternative for macOS, Windows, Linux and Android. It runs locally on a native Rust engine with a GPU compositor and covers auto-captions with local Whisper, text-to-speech and voice cloning, background removal, keyframes, 100 effects and 4K export, with no watermark, account or upload. A built-in MCP server (concat --mcp) and a JSON-RPC API let AI agents and scripts edit video too.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Add styled auto-captions to Shorts and Reels, fully offline: https://dedupedai.com/use-cases/jub0t-concat/caption-short-videos-offline/
- Let Claude or another agent edit your video over MCP: https://dedupedai.com/use-cases/jub0t-concat/let-an-ai-agent-edit-video-over-mcp/
- Make a tutorial with a cloned voice-over and background removal: https://dedupedai.com/use-cases/jub0t-concat/voice-over-and-cutout-for-a-tutorial/

## How to add styled auto-captions to Shorts and Reels, fully offline with Concat

Repo: [jub0t/Concat](https://github.com/jub0t/Concat) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README

Install Concat, download a Whisper model once and get styled captions on the timeline without uploading footage.

**Who it is for:** A creator who posts short vertical videos and wants captions without paying for a subscription or uploading clips.

**The problem:** Popular editors put captions behind accounts, watermarks or cloud uploads.

**The outcome:** Captioned videos exported up to 4K with no watermark, made entirely on your own machine.

### Steps

1. Download Concat from the website or GitHub Releases for your platform
2. On macOS, if an unsigned build will not open, run `xattr -dr com.apple.quarantine /Applications/Concat.app`
3. Download a caption model size once from Settings
4. Drop in your footage and generate auto-captions; style them with title presets
5. Export as H.264, HEVC or AV1

### Prompt to paste into your agent

```text
Help me caption <video> in jub0t/Concat: pick a Whisper model size that fits my machine, generate captions, suggest a readable caption style for vertical video, and export at 1080x1920.
```

### Caveat

Concat is in beta, and Windows builds are not signed yet, so SmartScreen may warn on install.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jub0t-concat/caption-short-videos-offline/

## How to let Claude or another agent edit your video over MCP with Concat

Repo: [jub0t/Concat](https://github.com/jub0t/Concat) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Turn on Concat's built-in MCP server so your agent can cut, caption and arrange clips.

**Who it is for:** A developer or creator who wants to describe edits in plain words and have an agent do the timeline work.

**The problem:** Repetitive cuts, trims and caption passes eat hours, and most editors cannot be driven by an agent.

**The outcome:** An agent connected to Concat that performs edits on your project through MCP while you review in the editor.

### Steps

1. Install Concat
2. Start the MCP server with `concat --mcp` and follow docs/MCP.md to connect your agent
3. Ask the agent to split, trim and arrange clips on the timeline
4. Have it add captions, titles or voice cleanup
5. Review the result in the preview and export

### Prompt to paste into your agent

```text
Connect to jub0t/Concat over MCP (concat --mcp), open <project>, cut the silences out of <clip>, add captions and a title card, and tell me every edit you made before I export.
```

### Caveat



Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jub0t-concat/let-an-ai-agent-edit-video-over-mcp/

## How to make a tutorial with a cloned voice-over and background removal with Concat

Repo: [jub0t/Concat](https://github.com/jub0t/Concat) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Use local text-to-speech, voice cloning and background removal to finish a screen recording or explainer.

**Who it is for:** A teacher or marketer making tutorials who does not want to record narration again for every edit.

**The problem:** Re-recording voice-overs for every script change is slow, and cutout tools usually need cloud uploads.

**The outcome:** A tutorial with narration in your own cloned voice, a cut-out presenter and clean audio, made locally.

### Steps

1. Install Concat and download the voice and cutout models from Settings
2. Clone a voice from a few seconds of your recording, or pick a free local voice
3. Generate the narration with text-to-speech from your script
4. Remove the background from your webcam footage and place it over the screen recording
5. Use one-switch voice cleanup to denoise and level loudness, then export

### Prompt to paste into your agent

```text
Plan a tutorial edit in jub0t/Concat for <topic>: write the narration script, list the steps to clone my voice and generate the voice-over, remove my webcam background, and arrange it picture-in-picture over the screen recording.
```

### Caveat



Risk, voice cloning: Only clone voices you own or have permission to use.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/jub0t-concat/voice-over-and-cutout-for-a-tutorial/