Practical overview
When it fits
Use Concat when you want a video editor that runs locally and combines editing tools with AI-assisted captions, speech generation and background removal.
Who it is for
- People editing videos with a local desktop or mobile application.
- Video creators who need captions, generated speech or background removal within an editing workflow.
- Developers exploring the application's documented JSON-RPC or gRPC API.
Documented uses
- Assemble and refine video using multiple tracks, keyframes, effects and titles.
- Add auto-generated captions or text-to-speech to a video workflow.
- Remove backgrounds and export finished video at resolutions up to 4K.
- Explore scripted control through the API documentation.
Requirements & limits
The homepage says the editor runs on the user's machine and requires no account. The listed platforms are Windows, macOS, Linux, Android and iOS.
- Local operation is a defining part of the documented workflow; the homepage says the app runs on the user's machine.
- The feature set combines conventional editing tools with auto-captions, text-to-speech and background removal.
- Export is documented up to 4K.
- The homepage identifies JSON-RPC and gRPC API documentation, but the available evidence does not specify API operations.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Add and correct automatic captions in Concat
Turn a clip's speech into timed captions and correct their wording.
Before you start
- A Concat project with a video or audio clip containing speech on its timeline.
- A downloaded Whisper transcriber model; the guide describes the documented Settings path.
Steps
If a transcriber model is not installed, open Settings from the top-right gear, choose Transcriber and download Base (English).
Select the timeline clip containing speech, then click Generate Captions, the T button on the timeline tray.
In the Captions panel, confirm the selected audio clip and pick a downloaded Whisper model.
Choose Bottom, Centre or Top for Placement and Small, Medium or Large for Size, then click Generate captions.
After the titles appear, select a caption on the timeline and correct its words in the Inspector's Text tab.
Expected outcome
After transcription succeeds, a title per spoken phrase appears on a free timeline lane and can be edited.
Guide limitations
- Speech recognition can mishear names or unclear speech; correct those words manually.
- These instructions follow the project documentation; OpenViST has not executed this workflow.
Generate timeline narration with Kokoro in Concat
Create narrated audio with a built-in Kokoro voice and add it to the timeline.
Before you start
- An open Concat project.
- The Kokoro voice model downloaded through Settings > Speech.
Steps
If no voice model is installed, open Settings from the top-right gear, choose Speech and download Kokoro.
Place the playhead where narration should start, then click the speaker button on the timeline tray to open Text to Speech.
Enter the narration in Script.
Choose Kokoro under Model and select one of its built-in voices.
Click Generate speech. When it completes, find the WAV under Generated > Speech in the Library and its audio clip on a free timeline lane.
Expected outcome
After generation succeeds, the WAV is available in the project audio folder and Library, with an audio clip on a free timeline lane.
Guide limitations
- Kokoro's documented built-in voices cover English and Chinese.
- These instructions follow the project documentation; OpenViST has not executed this workflow.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 22 October 2026
- Original website title
- Concat: the free, open-source CapCut replacement · Official homepage title · retained in its source language