top.toolboxes/subtitle-toolkit

up checked 2026-11-11T02:38:28.579Z

Unclaimed · Unverified

Publisher-provided title

Subtitle Toolkit

Publisher-provided description

Convert, clean, retime and validate SRT, WebVTT, ASS/SSA, SBV and TTML subtitles. 8 tools.

Summary by lookupd

Converts, cleans, retimes, merges, splits and validates subtitle files across SRT, WebVTT, ASS, SBV and TTML formats.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http subtitle-toolkit https://subtitle-mcp.toolboxes.top/mcp

Codex, remote (streamable-http)

codex mcp add subtitle-toolkit --url https://subtitle-mcp.toolboxes.top/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "subtitle-toolkit": {
      "url": "https://subtitle-mcp.toolboxes.top/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

convert_subtitle Convert subtitle text between formats. Reads SRT, WebVTT, ASS/SSA, YouTube SBV and TTML/DFXP; writes SRT, WebVTT, ASS, CSV or plain text. Format is auto-detecte
clean_subtitles Strip noise from auto-generated subtitles: HTML/WebVTT tags, ASS override codes, music and sound-effect cues, speaker labels, empty cues and duplicate lines. Re
retime_subtitles Fix subtitle timing. Use offset_seconds for a uniform shift (whole track early/late). Use ratio, or from_fps/to_fps, for progressive drift caused by a frame-rat
check_subtitle_timing Audit subtitle readability and produce a report: reading speed (CPS), cue durations that are too short or too long, lines that are too wide, more than two lines
merge_subtitles Append one subtitle track after another (CD1 + CD2, or a second language track). The second track is offset so it starts after the last cue of the first, plus a
split_subtitles Split one subtitle track into two parts at a given timecode, keeping original timecodes. Use the `at` argument plus `part` to fetch either half.
fix_subtitle_encoding Repair mojibake — text where UTF-8 bytes were decoded as a single-byte encoding (cp1252/Latin-1 or cp1251). Symptoms: "Ã©", "â€™", "Ð¿Ñ€Ð¸Ð²ÐµÑ‚". Returns the r
text_to_subtitles Turn a plain transcript (one line per caption) into an SRT file with evenly spaced timecodes. Timing is a starting point, not a real transcription — say so when

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/top.toolboxes/subtitle-toolkit.svg)](https://lookupd.com/servers/top.toolboxes/subtitle-toolkit)