All servers · Utilities · Audio & speech

Subtitle Toolkit

top.toolboxes/subtitle-toolkit · v1.0.0

Measured by MCP Station

Description written by the publisher, not verified

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

Connect

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

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

Tools as reported by the server

• 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-detected unless `from` is given.
• 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. Returns the subtitle file in SRT or WebVTT.
• 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-rate mismatch. Pass exactly one of the three.
• 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, and overlapping cues. Returns a formatted report listing every flagged cue.
• 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 an optional gap.
• 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: "é", "’", "привет". Returns the repaired text and how many passes were applied.
• 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 you present the result.

Website · JSON · Text for agents · Registry updated 2026-09-22