Update to PixVerse

{
  "description": "Desktop CLI required; unavailable in MCP-only sessions. Video localization: deliver the same video in another language with a rewritten script, native or narrated speech, re-timed captions and graphics, and typography that fits the target script.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 490
    },
    {
      "relative_path": "references/language-notes.md",
      "size_in_bytes": 1608
    }
  ],
  "name": "pixverse-video-translate",
  "skill_md_contents": "---\nname: pixverse-video-translate\ndescription: \"Desktop CLI required; unavailable in MCP-only sessions. Video localization: deliver the same video in another language with a rewritten script, native or narrated speech, re-timed captions and graphics, and typography that fits the target script.\"\n---\n\n# Video Localization\n\n## Execution Surface\n\nRead `../../skills-shared/execution-surface.md` before execution. Prefer a usable managed CLI.\n**Desktop required: do not activate this production skill in MCP mode.**\nTell the user that this workflow needs a desktop environment; recommend downloading\n[ChatGPT desktop](https://chatgpt.com/download/) and using the PixVerse plugin with a supported\nlocal executor and CLI. The desktop app alone does not prove local execution is available.\nStop before setup, paid calls or local steps. Only if the user explicitly accepts a different\nstandalone generation deliverable, select a supported skill from\n`../../skills-shared/mcp-workflow.md`. CLI mode retains the complete workflow below.\n\n\nWhen this workflow generates images or video, apply `../../skills-shared/quality-policy.md`:\nSunburst 2K/high for images, Seedance 2.5 1080p with automatic prompt enhancement for video,\nand a stopped upgrade/fallback choice for Free/Basic or model-entitlement rejection.\n\nThe same piece in another language, not a subtitle pass. The script is rewritten for the\ntarget audience, the performance is spoken in that language, and captions, boards, labels\nand sounds re-flow to the new words because they are bound to script anchors.\n\n## Installed Command\n\nBefore running helper commands, resolve the absolute plugin root from this `./SKILL.md` path: it is two directories above this skill directory and contains `.codex-plugin/plugin.json`. In every new shell session, set:\n\n```bash\nPVX=\"<absolute-plugin-root>/scripts/pvx\"\n```\n\nRun helper commands through `\"${PVX}\"`. Do not assume the user's current working directory is the plugin checkout, and do not bypass the installed wrapper with a module invocation.\n\n## Translate The Meaning\n\nRewrite with `../../skills-shared/semantic-script.md`, keeping the same segments and anchor\nnames so the plan needs no change. Translate punchlines and claims for effect, not word by\nword; keep numbers, names and product terms exact with `<shown|said>` readings. Cue breaks\nfollow the target language's reading rhythm: Chinese and Japanese phrases by meaning without\nspaces, Spanish and German with longer phrases and fewer, larger cues. Measure the new\nsegments; translations change length, so re-choose take durations.\n\n## Produce The Speech\n\n- **Native speech** (default when a person is on camera): regenerate each take through\n  `../pixverse-talking-head/SKILL.md` with the same host image and a voice reference in the\n  target language (`create voice` with a matching preset and `--language`).\n- **Narration over existing picture**: keep the accepted takes muted, generate narration with\n  `../pixverse-voiceover/SKILL.md`, and align it as an audio take so anchors come from the\n  narration. In the render plan use `base: {\"media\": \"<absolute original video path>\",\n  \"mute\": true}` and an `audio` layer pointing to the narration with `during: \"program\"`.\n  Recut or explicitly extend the picture to the measured narration duration before export;\n  a longer narration does not automatically extend the original picture.\n- **Dubbing an existing recording**: only when the user accepts that lips will not match;\n  otherwise choose native regeneration.\n\nReuse everything that does not speak through `../pixverse-video-variants/SKILL.md`.\n\n## Re-flow And Typeset\n\nRebuild the timeline with `--language <code>` (`../../skills-shared/word-timing.md`), then\nre-render the plan (`../../skills-shared/anchored-composition.md`). Captions pick a CJK face\nautomatically; check glyph coverage and line length for the target script, and pass\n`--size`/`--margin-v` when a longer language needs it. Re-render labels, stickers and board\ntext with the translated strings (`../../skills-shared/graphics-components.md`). Read\n`./references/language-notes.md` for per-language caption and timing rules.\n\nDeliver one file per language with its script, timeline and plan. Sample the same anchors in\nevery language to confirm reveals still land on the right words.\n\n## Execution\n\nRead `../../skills-shared/production-brief.md` for reference roles, prompt construction and revisions.\nFor media execution, follow `../../skills-shared/cli-workflow.md`; load the gateway before manual\nCLI commands or queue specs. Local media, script, timeline and graphics commands spend no credits.\nPrompt-only work ends with the usable plan and prompts; it needs no account or generation calls.\n"
}