Paste the text of an SRT subtitle file and get it back with lines reflowed for readability: split at natural phrase breaks, capped at your line length, with a flag on every cue that reads too fast for its duration. Your cue numbers and timestamps are kept exactly as pasted. It works on pasted text only. It does not transcribe audio, translate, burn captions into video, or upload files.
Not Google Translate. Not "good enough." This preserves a character's voice, catches cultural landmines before launch, generates titles that actually perform, translates the onomatopoeia most translators give up on, and adapts content across markets — built by a native Japanese speaker who ships to both Japan and overseas. Paste 5 lines of a character and watch it lock their voice forever. One question routes you to the right mode in seconds.
Local CSV, TSV, XLSX and JSONL redaction with Traditional Chinese instructions and reports. Preview first, then explicitly apply field removal, redaction or stable batch pseudonyms. No API required. Same engine as the English edition; choose one.
Check SRT files in batches, get cue-level QA reports, and export conservative repair copies while preserving your originals. Includes explicit time shifts, overlap trimming and two-line track splitting. English edition. Python 3.10+; no API key needed for the local engine.
Gets word-level STT with faster-whisper and re-splits cues by broadcast-style rules (max 2 lines, chars per line, CPS, min/max duration). In a 41.78 s sample, 7 raw whisper segments (up to 51 chars on one line) became 12 cues (up to 18 chars, 2 lines); STT word accuracy was 98.4%. The agent fills translation worksheets, so no API key; a script checks cue count and timecodes against the source and writes nothing if any differ. Burns in outline/box subtitles; QC: 0 issues in 3 languages.
母語級中文在地化：把英文（或任何來源）文案做成市場可用的繁中（台灣／香港）或簡中（中國大陸）成品——文化轉譯（transcreation）而非逐字翻譯、zh-TW vs zh-CN 用語選對、術語表一致、在地化慣例（日期／貨幣／數字／全形標點）、跨地區敏感用語把關。
I'm a Ugandan entrepreneur and native Luganda speaker who built this agent from a live content operation — not theory. Every phrase was native-verified. Tested across DC Couture Uganda's sales scripts and Marie Jacinta Nampijja's 5-day/week TikTok & Instagram calendar before publishing. Built on authentic code-switch linguistics, not English translation. This is the tool I use in my own business.
用途： 从 B站、抖音、小红书、TikTok、YouTube 视频，或用户提供的本地视频/音频中，提取可阅读、可编辑的中文或多语言口播文稿。 交付重点： 还原实际说话内容；保留原意、顺序和说话人区分；对听不清、无法访问或无法确认的部分明确标注，不猜写、不补写。