SmartSub - An open-source, one-stop desktop tool for audio and video subtitling.

What is SmartSub?

SmartSub is an open-source, one-stop desktop tool for audio and video subtitling. It integrates the entire process into a single application, using local models such as Whisper, FunASR, and Qwen3-ASR for offline speech-to-text conversion. It supports over 20 translation services and multi-character AI voice-over. SmartSub includes a built-in online video downloader, is compatible with platforms like Bilibili and YouTube, supports hardware acceleration such as NVIDIA CUDA and Apple Core ML, and runs locally across Windows, macOS, and Linux platforms.

Main functions of SmartSub

• Speech transcriptionIt is based on six local engines, including whisper.cpp, FunASR, and Qwen3-ASR, for offline recognition and supports automatic detection and batch processing of multiple languages.
• Subtitle TranslationIt integrates with 20+ translation services (including DeepSeek, Ollam, Tongyi Qianwen, etc.) and outputs pure translations or bilingual subtitles of the original text plus the translation.
• AI proofreadingIt features a built-in visual proofreading panel that automatically synchronizes and positions subtitles while playing videos, supports sentence-by-sentence editing, AI one-click polishing, and alignment with reference documents.
• TTS voice actingLocal Kokoro/VITS offline synthesis, supporting ZipVoice zero-sample voice cloning, multi-role timbre assignment, and speaker recognition.
• Subtitle burningHard subtitles are rendered directly into the screen, while soft subtitles are losslessly encapsulated in MKV format, supporting real-time preview of font, color, position, and other styles.
• Online downloadIt has a built-in yt-dlp/lux dual engine, allowing you to batch download videos and official subtitles by pasting links from Bilibili, YouTube, etc.
• Custom ProcessIt allows for the free combination of transcription, translation, proofreading, dubbing, and synthesis steps, which can be saved as a recipe for one-click reuse.

Follow us on WeChat and reply with "open source",join inAI open source project discussion group

How to use SmartSub

• Download and installInstall from GitHub Releases by selecting the corresponding system version (Windows/macOS/Linux). macOS is also supported. brew install --cask smartsub。
• Download ModelOn first launch, select and download the speech recognition model on the "Engine & Model" page.
• Configuration translationGo to "Settings → Translation Service", select the engine and enter the API Key.
• Create taskIn the launcher, select preset cards such as Video → Dubbed Movie, or customize the workflow combination target.
• Drag and drop filesDrag local videos/audio files to the task card, or paste Bilibili/YouTube links to automatically download them.
• Adjust parametersSelect the transcription engine, target language, whether to use bilingual subtitles, voiceover timbre, and subtitle style.
• Start processingClick "Start Task" and the application will automatically execute the transcription → translation → proofreading → dubbing → compositing pipeline.
• Proofreading and ExportCheck and modify each sentence in the proofreading panel, and then export the finished video with subtitles or dubbing after confirmation.

SmartSub's core advantages

• End-to-end local closed loopTranscription, translation (Ollama), dubbing, and burning can all be done offline.
• Engine switchingIt supports 6 transcription engines, 20+ translation services, and 5 types of dubbing solutions, which can be flexibly combined according to language scenarios and hardware conditions.
• Hardware acceleration full coverageSupports NVIDIA CUDA, AMD/Intel Vulkan, and Apple Core ML/Metal; one-click installation of the acceleration package within the application.
• Run at zero costLocal model + built-in free translation + local TTS, the entire pipeline can be used without paying for the API.
• Multi-character voice actingv3.7.0 supports speaker recognition and batch assignment of voice to roles, and individual voice overwrite can also be applied to a single sentence.

SmartSub's project address

• Project official website：https://smartsub.linxiaodong.com/
• GitHub repository：https://github.com/buxuku/SmartSub

SmartSub's Competitive Product Comparison

SmartSub application scenarios

• Foreign language video localizationTranscribe and translate unsubtitled online courses and documentaries into bilingual subtitles, or directly dub them to generate Chinese/foreign language audio tracks for overseas distribution.
• Podcast and Meeting TranscriptsThis function can batch transcribe long audio files into SRT text for content retrieval, editing, or text archiving.
• Self-media subtitle creationIt can quickly generate and burn finely edited subtitles for Bilibili/YouTube videos, and supports preset styles for multiple platforms.
• Online educational coursewareAdd multilingual voiceovers and bilingual subtitles to instructional videos, and maintain the consistency of the instructor's voice through voice cloning.
• Film and television adaptation and translationAfter downloading online videos, official subtitles are automatically matched, and the videos are translated, refined, and then either burned to disk or packaged in software for release.