Verified project record

buxuku/SmartSub

A desktop subtitle application for transcribing audio/video, translating subtitles, proofreading, and burning or embedding subtitles into video. It runs locally on Windows, macOS, and Linux with optional GPU acceleration and optional cloud-based transcription or translation services.

Project overview

Consolidates transcription, translation, proofreading, and video synthesis into a single local desktop GUI, with support for 7 selectable transcription engines and automatic GPU acceleration package management.

Project type: Workflow · Video · Audio & Speech
Use cases: Meeting Notes · Translation & Subtitles · Video Creation · Audio & Speech
Deployment: Refer to project documentation
License: MIT

Best for

General users, creators, and developers who need a desktop GUI to handle local transcription, translation, and subtitle burning in a single workflow.

Key capabilities

Provides GPU acceleration for transcription using NVIDIA CUDA, AMD/Intel Vulkan, and Apple Core ML/Metal, with automatic fallback to CPU.
Includes a built-in proofreading station for sentence-by-sentence review, editing, and AI-powered text refinement.
Burns subtitles into video as hard subs or embeds them as switchable soft sub tracks with styling controls.
Allows configuring custom request headers and body parameters for each AI translation service directly in the GUI.

Limitations and risks

Mac Intel devices only support CPU mode and do not support GPU acceleration.
When using cloud dictation services, audio is uploaded to third-party endpoints, presenting privacy implications for sensitive content.

Getting started

Setup is rated easy. Users download the OS-specific installer, run the application, follow the beginner guide to download a voice model, drag and drop files, set parameters, and start processing.

Alternatives and comparisons

Provides a one-click workflow for video translation and audio transcription supporting local offline deployment and online APIs.
Offers an automated pipeline to generate single-line subtitles and high-quality dubbing for videos.
Provides a one-stop desktop GUI tool for video subtitling, including speech recognition, optimization, translation, and synthesis.

Project comparisons

Evidence and sources

GitHub project description
README
README
README
README

Reviewed at: 2026-07-16T07:22:13Z

Open original GitHub project