What does Translating subtitles — SRT to clean, sentence-bounded SRT do?
Translate source SRT to target language with punctuation-bounded re-segmentation so no cue ends mid-sentence; bilingual SRT option for review.
Translate an SRT or transcript into another language (or a bilingual SRT) and re-segment so every cue ends at a real punctuation mark. Simplified Chinese and English are first-class. Text only: no audio, no burn-in.
Video Localization recipe step 2 (translate the words), from jianshuo/claude-skills (wjs-translating-subtitles, part of a 13-skill video production set). Source SRT in, target or bilingual SRT out. It translates for meaning in subtitle-style language at reading speed (about 15 Chinese characters or 40–42 English characters per line, two lines max), keeps names, brands, numbers and tone, strips the filler 这/那 that machine translation adds to Chinese, and re-segments Whisper's breath-based cues so each one ends at punctuation, splitting or merging cues and interpolating timestamps. Output follows strict SRT rules (sequential numbers, comma milliseconds, no overlaps). Burn-in and dubbing are separate skills.
npx skills add https://github.com/jianshuo/claude-skills/tree/main/wjs-translating-subtitlesTranslate source SRT to target language with punctuation-bounded re-segmentation so no cue ends mid-sentence; bilingual SRT option for review.
This repo contains 5 individual skills — each has its own dedicated page.
Thin orchestrator for end-to-end video localization: routes to wjs-transcribing-audio → translating-subtitles → dubbing-video → burning-subtitles. 131★ suite.
Agent skill at wjs-overlaying-video/SKILL.md
wjs-transcribing-audio: audio/video → source-language SRT (Whisper). Step 1 of jianshuo localization suite. 131★.
One-encode final localize cut: burn hardsubs (libass) and/or soft-mux, mix TTS dub over original audio bed.
Time-aligned TTS dub from a target-language SRT: Volcano (豆包) for Chinese, edge-tts for any language, atempo cue fit.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.