Who it is forA creator who posts short vertical videos and wants captions without paying for a subscription or uploading clips.
The problemPopular editors put captions behind accounts, watermarks or cloud uploads.
The outcomeCaptioned videos exported up to 4K with no watermark, made entirely on your own machine.
What you need first
- macOS, Windows, Linux or Android (iOS sideloaded)
- AI models for captions, voices and cutout download once from Settings, then work offline
- To build from source: Rust 1.93+, FFmpeg 7+ development libraries, cmake and a C++ compiler
Steps
- Download Concat from the website or GitHub Releases for your platform
- On macOS, if an unsigned build will not open, run
xattr -dr com.apple.quarantine /Applications/Concat.app - Download a caption model size once from Settings
- Drop in your footage and generate auto-captions; style them with title presets
- Export as H.264, HEVC or AV1
Prompt for your agent
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.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for jub0t/Concat and "Add styled auto-captions to Shorts and Reels, fully offline"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer