Concat social preview
tts-stt10,559AGPL-3.0

Concat

The truly free, open-source, local-first, cross-platform CapCut replacement. Scriptable through a JSON-RPC API & MCP.

Updated Oct 22, 2026
Website GitHub Docs
Platforms
macos, linux, windows
Pricing
free-open-source
Status
active
License
AGPL-3.0

What it does

Core capabilities at a glance

  • Ffmpeg
  • Free Video Editor
  • Model Context Protocol
  • NON Linear Editor
  • Offline First
  • Open Source Video Editor
  • Self Hosted
  • Video Editing

Deep dive

The full breakdown - performance, comparisons, and setup

Concat

Concat is a speech (TTS/STT) tool - The truly free, open-source, local-first, cross-platform CapCut replacement. Scriptable through a JSON-RPC API & MCP.

Overview

Concat The free, open-source, cross-platform CapCut replacement.

Concat is a free, open-source video editor and a CapCut alternative for macOS, Windows, Linux and Android. It covers what people actually open CapCut for: auto-captions, text-to-speech, background removal, keyframe animation, effects and titles, multi-track cutting, 4K export. With none of the catches: no watermark, no account, no subscription, no upload.

Everything runs locally on a native Rust engine with a GPU compositor. Install it, drop in footage, cut. The AI models for captions, voices and cutout download once from Settings and work offline after that. Your footage never leaves your disk.

Good for: TikTok, Reels and Shorts, YouTube videos, tutorials and screen recordings, podcast clips, memes.

Also for machines: a built-in MCP server for AI agents ('concat --mcp', set up) and a JSON-RPC API for scripts, so they can cut video with it too.

Concat is open-source, written primarily in Rust, with 10,559 GitHub stars under the AGPL-3.0 license. The latest release is v0.2.8 (2026-10-20).

Key capabilities

From the project's documentation:

  • 🚫 No watermarks. No account. No paywall. Ever.
  • 🔒 100% local. Nothing uploads. Works offline.
  • 💬 Auto-captions. Local Whisper. Pick a model size, get styled captions on the timeline.
  • 🗣️ Text-to-speech + voice cloning. Free local voices, or any voice from a few seconds of a recording.
  • 🧍 Background removal. People, objects, or paint the mask yourself.
  • 🎞️ Keyframes. Position, scale, rotation, opacity, volume, effect parameters. Curve editor built in.

Install

A quick way to get started (always check the official docs for the latest):

brew install ffmpeg

How it fits a local-AI stack

Concat runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:

Sources

Stats from GitHub, 2026-10-22.

Frequently asked

Quick answers to common questions

What is Concat?

Concat is a tts-stt tool for local AI workloads. The truly free, open-source, local-first, cross-platform CapCut replacement. Scriptable through a JSON-RPC API & MCP.

Is Concat free and open source?

Yes, Concat has 10,559 GitHub stars and is licensed under AGPL-3.0. You can self-host it for free on macos, linux, windows.

What platforms does Concat support?

Concat runs on macos, linux, windows.

What hardware do I need for Concat?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. Concat has 10,559 GitHub stars and an active community.

Does Concat support GPU acceleration?

Concat supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to Concat?

Popular alternatives include other tts-stt tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does Concat cost?

Concat is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware