#3535th of 49 in Desktop AI appsFor image, video and design, video and animation, voice, speech and music

smartsub

Desktop app for subtitle transcription, translation, dubbing and burn-in

Stars
6k
License
MIT
Last commit
Nov 2026
Last release
Nov 2026
Language
TypeScript
Stars, last 29 weeks+2,345
21 Apr 2026: 3,667 stars28 Apr 2026: 3,687 stars5 May 2026: 3,744 stars12 May 2026: 3,825 stars19 May 2026: 3,845 stars26 May 2026: 3,860 stars2 Jun 2026: 3,881 stars9 Jun 2026: 3,909 stars16 Jun 2026: 3,921 stars23 Jun 2026: 4,020 stars30 Jun 2026: 4,108 stars7 Jul 2026: 4,165 stars14 Jul 2026: 4,213 stars21 Jul 2026: 4,262 stars28 Jul 2026: 4,328 stars4 Aug 2026: 4,418 stars11 Aug 2026: 4,564 stars18 Aug 2026: 4,667 stars25 Aug 2026: 4,739 stars1 Sept 2026: 4,821 stars8 Sept 2026: 4,934 stars15 Sept 2026: 5,146 stars22 Sept 2026: 5,283 stars29 Sept 2026: 5,401 stars6 Oct 2026: 5,551 stars13 Oct 2026: 5,669 stars20 Oct 2026: 5,776 stars27 Oct 2026: 5,865 stars3 Nov 2026: 5,935 stars10 Nov 2026: 6,012 stars

3,667 on 21 Apr 20266,012 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

SmartSub is an Electron desktop app that runs a subtitle pipeline: download online video, transcribe locally (whisper.cpp, faster-whisper, FunASR, Qwen3-ASR, FireRedASR, Parakeet), translate, proofread, dub with TTS and voice cloning, then burn or mux subtitles with ffmpeg. It has an in-app AI assistant and exposes 111 MCP tools and a smartsub CLI so external agents or scripts can drive the same pipeline.

Who it is for: Video creators and translators who want local subtitle and dubbing workflows

Strengths

  • Full local path: transcription, TTS, voice cloning and ffmpeg burn-in need no API key
  • Seven local transcription engines switchable per task, plus 9 optional cloud ASR providers
  • 111 MCP tools and a smartsub CLI with headless daemon for Cursor, Claude Code, Codex, CI
  • GPU acceleration via CUDA, Vulkan or Core ML/Metal, with CPU fallback on load failure

Weaknesses

  • Intel Mac build is CPU only, no GPU acceleration
  • Free translation uses unofficial Youdao/Bing/Google endpoints; Edge TTS availability not guaranteed
  • README is primarily Chinese; English and Japanese READMEs are separate files
  • Desktop only; no Docker image or web server deployment

What it needs

  • GPU optional
  • Needs yt-dlp, lux, Ollama (optional)
  • Models: whisper.cpp ggml, faster-whisper, FunASR, Qwen3-ASR, FireRedASR

Quick answers

Is smartsub open source?

Yes. Its code is on GitHub under the MIT license.

Does smartsub need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Also in Desktop AI apps

See all 49
Also in Desktop AI apps
RankProjectScore
1cherry-studioDesktop client for chatting with many LLM providers, with agents and knowledge bases53.4k stars+1,124 (+2.1%) in 30 daysAGPL-3.092 out of 100
2dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness, built on plugins35.7k stars+5,734 (+19%) in 30 daysMIT90 out of 100
3screenpipeRecords screen and audio locally, makes it searchable for you and your agents22.3k stars+481 (+2.2%) in 30 dayscustom license90 out of 100
#4prompt-optimizerPrompt rewriting and testing tool for web, desktop, Chrome and MCP Live demo ↗ (opens in a new tab)41.2k stars+3,703 (+9.9%) in 30 dayscustom license86 out of 100
#5aionuiDesktop and WebUI app that runs a built-in agent plus external CLI agents34.2k stars+923 (+2.8%) in 30 daysApache-2.086 out of 100