KrillinAI: Open-Source AI Video Translation and Dubbing for Humans and AI Agents
100+ languages. Runs locally. $0.
It’s called KrillinAI. You give it a YouTube link or local video and it handles the full workflow from transcription to a finished localized video.
→ Transcribes with Whisper options
→ Translates into 100+ languages
→ Generates TTS dubbing
→ Creates horizontal and vertical versions
→ Generates platform cover images
→ Works on Windows, macOS, and Linux
→ Includes CLI skills for AI agents
The interesting part is the agent workflow.
Each stage can run separately, so coding agents can chain subtitles, dubbing, rendering, and cover generation into automated pipelines.
Link: https://lnkd.in/evG9u8EH
It supports local speech recognition and OpenAI-compatible local or cloud LLMs.
100% Open Source.
KrillinAI: Open-Source AI Video Translation and Dubbing for Humans and AI Agents
KrillinAI is an open-source video localization tool designed to automate much of the process of translating and dubbing videos.
You can provide a YouTube/Bilibili link or a local video, and KrillinAI can handle multiple stages of the workflow:
→ Transcribe speech using Whisper-based options
→ Translate subtitles using LLMs
→ Generate dubbed audio using supported TTS providers
→ Create landscape and portrait versions
→ Generate platform cover images
→ Run individual stages through its CLI
→ Chain multiple stages into automated workflows for AI agents
The project supports Windows, macOS, and Linux and provides local speech-recognition options such as FasterWhisper and WhisperCpp. It can also connect to local or cloud LLMs that provide OpenAI-compatible APIs.
One of the more interesting aspects is its agent-oriented workflow. Instead of treating video dubbing as one large operation, KrillinAI exposes individual stages such as subtitle generation and TTS through its CLI, allowing AI agents and automation scripts to reuse outputs between stages.
It currently advertises translation support for 100+ languages, although the supported input languages and available TTS providers/voices are more limited and depend on the configured services.
The "zero-cost" claim needs some clarification: KrillinAI itself is open source, and using local models can eliminate cloud API charges, but using cloud LLM or TTS providers may still incur costs.
The bigger idea isn't simply AI dubbing—it's the ability to turn video localization into a programmable, agent-driven pipeline.