An LLM agent-driven subtitle finder, evaluator, and translator for local media.
Autonomous LLM agent that finds, validates, installs, and translates media subtitles.
Subtitle Scout is a self-hosted subtitle management system driven by an LLM agent. It targets media collectors and engineers managing local video libraries who want automated, context-aware subtitle matching rather than rigid pipeline searches.
Instead of relying on top search hits, the tool's core agent downloads subtitle candidates into a sandbox, checks timeline spans and cue counts, and evaluates structural fit for exact episodes. When no source exists, a secondary agent handles sentence-by-sentence translation using custom glossaries.
It suits power users and technical media managers tired of mismatched release groups or missing translations. It does not suit users looking for a simple point-and-click desktop app without Docker or API keys.
Downloads candidates into a sandbox to judge exact episode fit based on timeline span and cue structure.
Queries OpenSubtitles, SubDL, ASSRT, r3sub, Jimaku, SubHD, and Zimuku depending on your target language.
Translates subtitles sentence by sentence using a glossary pass when no source tracks are available.
Scans your media directories directly without requiring Plex, Jellyfin, Emby, Sonarr, or Radarr.
Free under its open source licence. The only cost is running the hardware and paying for the LLM and API tokens you consume.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
No, Subtitle Scout scans your media folders directly and operates entirely independently.
Chinese has the deepest coverage, with full support for English, Japanese, and Korean, plus basic support for several European languages.
Models below frontier mini or flash tiers tend to fabricate match results, leading to misidentified media.
See Zekai first in Google