What it does
SmartSub (妙幕) turns the speech in audio and video into subtitles using models such as Whisper that run on your own computer, so files don't leave your machine. It can then translate the subtitles, help you proof-read them, and burn them into the video.
It can also create a new voice track from the subtitles with text-to-speech, including cloning a voice from a short recording. A built-in AI assistant helps edit subtitles and fix problems, and other AI tools can control it through MCP.
Its makers say the whole process can run free with local models, and you can add online translation, transcription or voice services if you like.
Who it's for
Video creators, translators, students and anyone who needs subtitles or dubbing for videos, podcasts or lectures.
Can I use it without coding?
Yes. There are installers for Windows, Mac and Linux. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Mac, Linux
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Download the installer for your computer from the project's releases page.
- Follow the welcome guide to download a speech model.
- Drag in a video or audio file, choose the languages, and start.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page or the official download page above. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe