SmartSub
Free, MIT-licensed subtitle and dubbing app for Windows, macOS and Linux, with offline transcription, local voice synthesis and optional cloud services.
SmartSub is a free, open-source desktop app for people who subtitle recordings or adapt videos into other languages. It combines local transcription, translation, subtitle editing and AI dubbing on Windows, macOS and Linux. Each stage also works independently.
Local speech recognition uses whisper.cpp, faster-whisper, FunASR, Qwen3-ASR or FireRedASR. Once downloaded, these models work offline and process files on your machine. Batch processing supports NVIDIA, AMD, Intel and Apple Silicon GPU acceleration; cloud transcription is an optional alternative.
Translation can use built-in free services, Ollama for a local LLM, or providers such as DeepSeek and Gemini. Glossaries help keep names and terminology consistent, and bilingual output preserves both languages. The editor pairs subtitle lines with video playback and supports timing edits, search and replace, merging and splitting, plus AI proofreading.
Kokoro and VITS synthesize speech locally and offline. Voice cloning includes ZipVoice and optional cloud services such as ElevenLabs. The app aligns generated speech with subtitle timing, then uses local ffmpeg processing to mix audio and export videos with burned-in or selectable subtitles. Style previews show how captions will look before export.
The MIT-licensed app doesn't require an account or API key for its free workflow. Cloud services process the tasks you send to them; local transcription and voice synthesis stay on your hardware. It also downloads YouTube and Bilibili videos with matching platform subtitles, and exposes MCP and CLI automation for tools such as Cursor and Claude Code.
