Wjs Translating Subtitles

wjs-translating-subtitles

Source-language SRT in → target-language (or bilingual) SRT out. This skill is text-only. Burn-in lives in /wjs-burning-subtitles; voice dub in /wjs-dubbing-video.

When to use

• User has an SRT in language A and wants it in language B.
• User pasted a transcript (with or without timestamps) and wants a translation that becomes an SRT.
• User has an SRT but cues end mid-sentence — this skill's re-segmentation step fixes that.

When NOT to use

• No source-language SRT yet → run /wjs-transcribing-audio first.
• User wants burned-in subtitles → finish translation here, then /wjs-burning-subtitles.
• User wants voice dub → finish translation here, then /wjs-dubbing-video.

Pick the target

Resolve target from the user's phrasing once, don't re-ask:

• "翻成中文 / 中文字幕 / 中文配音" → zh-CN.
• "translate to English / English subs / English dub" → en.
• "bilingual" / "双语" → produce both .<source>.srt and .<target>.srt (and optionally a combined .<source>-<target>.srt).
• Ambiguous → default to whichever the user has historically chosen in the project.

Simplified Chinese and English are fully validated. Other targets (Japanese, Korean, French, etc.) work via the same rules; the bottleneck is TTS-voice availability if dubbing follows — see /wjs-dubbing-video before promising.

Shared translation principles

• Prioritize meaning over literal wording.
• Use concise subtitle-style language — viewers read at ~3 wps for Chinese, ~3–4 wps for English; lines that exceed that go off-screen before they can be read.
• Preserve the tone of the speaker. Casual source → casual target; formal source → formal target.
• Do not over-translate names, brands, cultural references, or technical terms.
• Keep numbers, dates, names, and places accurate.
• If a phrase has no exact equivalent, translate the meaning naturally. No literal/word-for-word constructions.
• Avoid stiff, machine-translated output.

Translating into Simplified Chinese (zh-CN)

• Use natural spoken Mandarin for casual speech, formal Mandarin for formal speech.
• Use Simplified characters only (do NOT use Traditional Hanzi unless the user explicitly asks).
• Subtitle lines should be roughly 15 Chinese characters or fewer per line, max 2 lines per cue (3 only when unavoidable for very long cues).
• Use Chinese punctuation: 「，」「。」「；」「：」「、」「——」. Never mix English commas/periods into Chinese subtitles.
• Minimize filler demonstratives 「这」「那」「这个」「那个」「那份」「那种」「那里」「那样」. Spanish-to-Chinese (and English-to-Chinese) MT routinely inserts these because the source has overt demonstratives that Chinese usually drops. Examples:
  • "这把我们带入二元世界的载体" → "把我们带入二元的载体"
  • "运用那份能量" → "运用这股能量" if needed, or just "运用能量"
  • "正是在这合一里" → "正是在合一中"
  • "像罪人那样翻滚" → "像罪人翻滚" / "像罪人般翻滚"
  • "那份精微的觉知" → "精微的觉知" Keep them only when they carry real meaning (deixis, contrast, or fixed phrase like spiritual "我就是那" / "tat tvam asi"). Default is to delete; add back only if the sentence becomes ambiguous.

Examples (Spanish → Chinese):

Spanish: No pasa nada.            → Chinese: 没关系。
Spanish: Vamos a ver qué pasa.    → Chinese: 我们看看会发生什么。
Spanish: Me parece una locura.    → Chinese: 我觉得这太疯狂了。
Spanish: ¿Qué quieres decir?      → Chinese: 你是什么意思？
Spanish: La verdad es que no lo esperaba.
                                  → Chinese: 说实话，我没想到会这样。

Translating into English (en)

• Use natural conversational English. Avoid translationese ("It is precisely through entering the body…" → "It's by entering the body…").
• Lines should be roughly 40–42 characters or fewer (about 7–9 words), max 2 lines per cue. Hard cap 50 chars per line.
• Use ASCII punctuation: , . ; : — (em-dash). Avoid Unicode curly quotes — keeps .srt portable.
• For contemplative/spiritual content, prefer plain words over Latinate jargon: "presence" over "manifestation," "wholeness" over "totality," "wake up" over "awaken to consciousness."

Examples (Spanish → English):

Spanish: No pasa nada.            → English: It's nothing.
Spanish: Vamos a ver qué pasa.    → English: Let's see what happens.
Spanish: Me parece una locura.    → English: This feels crazy to me.
Spanish: ¿Qué quieres decir?      → English: What do you mean?
Spanish: La verdad es que no lo esperaba.
                                  → English: Honestly, I wasn't expecting this.

Re-segment at punctuation boundaries (mandatory)

Whisper segments by silence/breath, not grammar. The result almost always has cues that end mid-sentence (e.g., "...es una forma de aterrizar," next cue starts "el espíritu en el cuerpo..."). Any TTS that processes one cue at a time will then insert an unnatural pause exactly where the original speaker did not. The fix is mandatory before dubbing — and improves on-screen reading too.

Punctuation set differs:

• Chinese cues must end at ， 。 ； ： —— or 、.
• English cues must end at , . ; : — (em-dash) or, in practice for subtitles, occasionally a single dash. Never end an English cue on a comma-less clause break, and never split inside a phrase like "kind of" or "in order to".

Rules:

• Every cue must end at a real punctuation mark. Never let a cue end on a noun, verb, conjunction, or article that flows into the next cue.
• It is fine (and often necessary) to split a single source cue into 2–4 shorter cues, with timestamps interpolated by character position within the original cue's duration.
• It is fine to merge the tail of one source cue with the head of the next when they form one clause — the merged cue inherits the start of the first and the end of the second.
• Target 3–8 seconds per cue. Cues shorter than ~1.5s feel choppy on screen; cues longer than ~10s usually contain a missed punctuation break.

A typical 2–3 minute talk yields roughly 25–40 punct-bounded cues from 12–18 raw source cues. Don't try to keep the original cue count.

When TTS dubbing follows: the punctuation-bounded structure means each TTS clip is a complete utterance with proper end-intonation, and concatenating clips sounds natural because every join is at a real pause point.