An open-source desktop app for video transcription, translation, and AI dubbing.
Generate, translate, dub, and burn video subtitles locally with GPU acceleration.
SmartSub is a cross-platform desktop application that manages your entire video localization pipeline from transcription to subtitle burning. It is designed for urban planners, municipal communications teams, and public sector creators who need to process public meeting recordings or smart city documentation locally.
The tool handles local speech-to-text transcription using whisper.cpp or FunASR, translates text across multiple engines, and provides AI dubbing with voice cloning. It also features an AI assistant with multi-modal vision diagnostics and MCP automation support.
It suits government agencies and municipal video teams needing strict local data privacy for public meetings. It does not suit teams looking for a cloud-native collaborative web editing suite without desktop client installations.
Transcribe audio offline using Whisper, FunASR, or FireRedASR models to keep municipal data private.
Use natural language commands or integrate with external AI agents via 111 standard MCP tools and CLI.
Generate custom audio tracks and clone voices using local engines like Kokoro, VITS, or ZipVoice.
Download online videos from platforms via yt-dlp and burn hard or soft subtitles directly into footage.
Free under its license, with optional paid cloud APIs available if you choose to connect commercial translation or TTS providers.
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Yes, local transcription models, offline TTS, and ffmpeg burning operate entirely without an internet connection.
No, the core transcription, local translation options, and local TTS engines run completely free without API keys.
You can utilize the built-in smartsub CLI commands and standard MCP protocol tools to execute pipelines.
See Zekai first in Google