subtitle-scout
A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to the exact episode, installs the one that fits, and translates when no source has it.
A self-hosted subtitle automation system with an LLM agent at its core — it identifies your media, judges whether each candidate belongs to the exact episode, installs the one that fits, and translates when no source has it.
Translate documents, parse PDFs, and extract text with OCR.
Key features
- LLM agent 判定字幕归属
- 多字幕源智能选择
- 无源时逐句翻译
- 中英日韩全支持
- Docker 一键部署
- 配 agent skill 自动部署
Good for
- 媒体库字幕自动化
- 中文字幕匹配
- 字幕翻译
- NAS 影音管理
Stack & tags
Node.jsDockerSQLiteLLMTMDBAgent Skillsai-agentchinese-subtitlesdockerllmopensubtitlesself-hostedsubtitle-translationsubtitles
Quick start
git clone https://github.com/fancydirty/subtitle-scout && cd subtitle-scout
mkdir -p cache && cp .env.example .env
docker compose up -dFrom the project README on GitHub.
Similar open-source projects
微软 MarkItDown
★ 187,737Microsoft's open-source Python tool — convert PDF/Word/PPT/audio/YouTube to clean Markdown
DeepSeek-OCR
★ 23,926DeepSeek's novel OCR document model — "contextual optical compression"