Skip to content
SPECIFICTION
Get listed

SmartSub

github.com

Free plan Open source WindowsmacOSLinuxAPI
Visit github.com
Spec score 9.0 #6 of 99 in AI Video Caption Generators

What it is

SmartSub is an open-source desktop app for transcription, subtitle translation, proofreading, AI dubbing and video subtitle rendering. It runs on Windows, macOS and Linux, and is free with no local usage limits. For local processing, its maker says models process files on the user's computer, so those files do not leave the device. Transcription options include whisper.cpp, faster-whisper, FunASR, Qwen3-ASR and FireRedASR. Translation includes 20 services, including built-in free translation and integrations such as DeepSeek, Gemini and Ollama. The proofreading workspace offers video-synced editing, undo and redo, search and replace, and AI proofreading. SmartSub can generate speech from subtitle lines, align audio to the timeline and clone voices with ZipVoice, Volcengine or ElevenLabs. It can burn subtitles into video or package soft subtitles, preview styles and include dubbed audio. It also downloads videos from links using yt-dlp and lux, supporting more than 1,800 sites. Cloud transcription uploads audio to the configured provider endpoint; the README advises against using it for sensitive content.

Spec sheet

What it does
SmartSub combines video downloading, speech transcription, subtitle translation, proofreading, AI dubbing, voice cloning and subtitle rendering in one desktop application.Read 15 Oct 2026 · github.com
Purpose
SmartSub is an open-source desktop app for transcription, subtitle translation, proofreading, AI dubbing, and video subtitle rendering.Read 11 Oct 2026 · smartsub.linxiaodong.com
Free plan
YesRead 19 Sep 2026 · github.com
Maker
The GitHub account identifies the maker as Lin Xiaodong (buxuku), a frontend developer working in Chengdu.Read 15 Oct 2026 · github.com
AI assistant
The in-app copilot provides workspace context, conversational editing, screenshot diagnostics, file chat and tool execution.Read 15 Oct 2026 · github.com
AI-client integrations
The settings workflow can connect Cursor, OpenAI Codex and Claude Code through generated MCP configuration.Read 15 Oct 2026 · github.com
Automation
The repository README describes MCP and CLI automation with 111 tools and commands for media processing workflows.Read 11 Oct 2026 · github.com
Brand caption presets
YesRead 19 Sep 2026 · github.com
Burn-in captions
YesRead 19 Sep 2026 · github.com
Caption styling
YesRead 19 Sep 2026 · github.com
Cloud transcription privacy
For cloud transcription, audio is uploaded to the configured provider endpoint, and the README advises against using it for sensitive content.Read 11 Oct 2026 · github.com
Cloud voice services
Cloud dubbing options include Edge TTS, OpenAI-compatible endpoints, Azure Speech, Volcengine, ElevenLabs and Xiaomi MiMo.Read 15 Oct 2026 · github.com
Core workflow
Each stage can be run separately or chained into batch pipelines.Read 15 Oct 2026 · smartsub.linxiaodong.com
Developer build
Contributors clone the repository, run yarn install and yarn dev, with yarn native:fetch available when native downloads fail.Read 15 Oct 2026 · github.com
Documentation and support
The project publishes a Docusaurus documentation site with usage guides and FAQ pages and directs support to GitHub issues and community chat.Read 15 Oct 2026 · smartsub.linxiaodong.com
Dubbing
Local Kokoro and VITS engines provide 103 and 174 voices respectively, while ZipVoice supports zero-shot cloning from a reference clip.Read 15 Oct 2026 · github.com
GPU acceleration
The download guide lists CUDA for NVIDIA and Vulkan for AMD or Intel on Windows and Linux, and Core ML or Metal on Apple-silicon Macs.Read 11 Oct 2026 · github.com
Hardware acceleration
Acceleration paths include NVIDIA CUDA, AMD/Intel Vulkan and Apple Core ML/Metal, with CPU fallback when acceleration fails.Read 15 Oct 2026 · github.com
Installation
macOS users can install through Homebrew using the buxuku tap and smartsub cask.Read 15 Oct 2026 · smartsub.linxiaodong.com
Intel Mac limitation
The Intel macOS build runs CPU-only and does not support GPU acceleration.Read 15 Oct 2026 · smartsub.linxiaodong.com
Licence
The repository is released under the MIT licence, with copyright attributed to Lin Xiaodong in 2024.Read 15 Oct 2026 · github.com
License and support
The project uses the MIT license and directs users to documentation, FAQs, community groups, GitHub issues, and pull requests for help or participation.Read 11 Oct 2026 · github.com
Limit: crashes
A GitHub issue reports tasks crashing around 20 percent completion even in CPU-only mode on older hardware.Read 15 Oct 2026 · github.com
Limit: external translation dependency
Hysen Labs noted that free Bing and Google translation endpoints are subject to rate limits and network reachability outside the project’s control.Read 15 Oct 2026 · hysenlabs.com
Limit: hardware dependence
The same review found CPU transcription slow, long videos more practical with a GPU and AMD/Intel Vulkan slower than NVIDIA CUDA.Read 15 Oct 2026 · swjsj.com
Limit: live captions
The independent review said SmartSub is unsuitable for real-time live-caption streams.Read 15 Oct 2026 · swjsj.com
Limit: manual dubbing review
Hysen Labs reported that over-long dubbed lines are placed in a manual review list rather than handled fully automatically.Read 15 Oct 2026 · hysenlabs.com
Limit: model downloads
A GitHub issue records repeated model-download failures and requests for easier direct-download or import workflows.Read 15 Oct 2026 · github.com
Limit: output quality
The review reported occasional punctuation errors, voice cloning weaker than ElevenLabs and local TTS below delivery-grade quality for professional dubbing.Read 15 Oct 2026 · swjsj.com
Limit: proofreading corruption
Another issue reports v3.9.0 proofread-cache JSON corruption that prevents opening the proofreading panel on Windows.Read 15 Oct 2026 · github.com
Limit: setup friction
The hands-on review said first use requires downloading models and configuring translation services, which creates a barrier for beginners.Read 15 Oct 2026 · swjsj.com
Local privacy
Local engines process files on the computer, while cloud services are optional and require a first-use privacy confirmation.Read 15 Oct 2026 · github.com
Local processing
The maker says local models process files on the user's computer, so files do not leave the device during local processing.Read 11 Oct 2026 · smartsub.linxiaodong.com
MCP and CLI
Version 3.9.0 added MCP and CLI automation with 111 tools, JSON or stdin pipelines, request deduplication and task polling.Read 15 Oct 2026 · github.com
Praise: format coverage
King of Computer Media reported exports for SRT, VTT, ASS, LRC and TXT alongside batch processing and local Ollama translation.Read 15 Oct 2026 · en.kocpc.com.tw
Praise: integrated workflow
Hysen Labs praised the single desktop pipeline covering download, transcription, translation, proofreading, dubbing and burn-in.Read 15 Oct 2026 · hysenlabs.com
Praise: local processing
Hysen Labs highlighted that local models keep media on the user’s machine and avoid mandatory cloud upload.Read 15 Oct 2026 · hysenlabs.com
Praise: practical speed
A hands-on review reported a 10-minute YouTube video completing the full pipeline in about seven minutes on an RTX 4060 with CUDA.Read 15 Oct 2026 · swjsj.com
Proofreading
The proofreading workspace supports video-synced subtitle editing, undo and redo, search and replace, and AI proofreading.Read 11 Oct 2026 · smartsub.linxiaodong.com
Release news
Release 3.9.0, shown on the releases page, introduced the AI assistant, MCP/CLI automation and an audio-video toolbox in September 2026.Read 15 Oct 2026 · github.com
Repository activity
The public repository page showed about 5.7 thousand stars, 458 forks and 612 commits when opened.Read 15 Oct 2026 · github.com
Speaker identification
YesRead 19 Sep 2026 · github.com
Subtitle editor
The editor supports video-synchronised line editing, undo/redo, deletion with restore and AI polishing.Read 15 Oct 2026 · github.com
Subtitle export
other formatsRead 19 Sep 2026 · github.com
Subtitle rendering
The app supports permanent burn-in and switchable soft subtitles with style controls and WYSIWYG preview.Read 15 Oct 2026 · smartsub.linxiaodong.com
Supported systems
The maker provides desktop builds for Windows, macOS, and Linux; the listed packages include Windows x64, macOS arm64 and x64, and Linux x64.Read 11 Oct 2026 · github.com
System packages
Downloads are provided for Windows x64, macOS Apple Silicon, macOS Intel and Linux x64, with GPU packs fetched after installation.Read 15 Oct 2026 · smartsub.linxiaodong.com
Transcription
It includes whisper.cpp and supports faster-whisper, FunASR, Qwen3-ASR, and FireRedASR as selectable transcription engines.Read 11 Oct 2026 · github.com
Transcription engines
Eight engine families are listed, including whisper.cpp, faster-whisper, FunASR, Qwen3-ASR, FireRedASR, NVIDIA Parakeet, local Whisper CLI and cloud ASR providers.Read 15 Oct 2026 · github.com
Translation
It offers 20 translation services, including built-in free translation and integrations such as DeepSeek, Gemini, and Ollama.Read 11 Oct 2026 · smartsub.linxiaodong.com
Translation extensibility
Users can supply any OpenAI-style endpoint and import or export per-service request parameters without code changes.Read 15 Oct 2026 · github.com
Translation integrations
The product lists 20 translation services, including free Bing/Google endpoints, Chinese vendors, DeepLX, Ollama, DeepSeek, Gemini, Qwen, Azure OpenAI and other OpenAI-compatible endpoints.Read 15 Oct 2026 · github.com
Video downloading
The app uses yt-dlp for YouTube and more than 1,800 sites and lux for Chinese platforms, with cookie import and automatic official-subtitle pairing.Read 15 Oct 2026 · github.com
Video downloads
It downloads videos from links including Bilibili and YouTube, using yt-dlp and lux, and supports more than 1,800 sites.Read 11 Oct 2026 · smartsub.linxiaodong.com
Video rendering
Users can burn subtitles into video or package soft subtitles, preview styles, and include a dubbed audio track.Read 11 Oct 2026 · smartsub.linxiaodong.com

Plans and prices

Free Free free local transcription, translation, TTS and FFmpeg workflow · no API key or usage limit for local steps · optional paid cloud providers Read 15 Oct 2026 · smartsub.linxiaodong.com

Every SmartSub plan and price →

Strong points and limits

Strong points

  • Free local use with no usage limits
  • Multiple selectable transcription engines
  • Subtitle editing is synchronized with video
  • Can burn or package subtitles and add dubbed audio
  • Desktop builds cover Windows, macOS and Linux

Limits

  • Cloud transcription uploads audio to the configured provider
  • The README advises against cloud transcription for sensitive content
  • Optional cloud services may be paid

Who it suits

SmartSub suits desktop users who need transcription, translation, subtitle editing or dubbing in one workflow. Its local processing option may suit users who want files to remain on their computer during processing.

Verdict

SmartSub combines subtitle creation, editing, translation and rendering with local processing and optional cloud services. Users considering cloud transcription should account for audio being uploaded to the configured endpoint.

Where Specifiction places it

Alternatives to SmartSubAll alternatives →