Update to PixVerse

{
  "description": "Voiceover: produce natural narration or explicitly timed takes, preserving pronunciation, voice continuity and measured timing for editing.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 292
    },
    {
      "relative_path": "references/production.md",
      "size_in_bytes": 5326
    }
  ],
  "name": "pixverse-voiceover",
  "skill_md_contents": "---\nname: pixverse-voiceover\ndescription: \"Voiceover: produce natural narration or explicitly timed takes, preserving pronunciation, voice continuity and measured timing for editing.\"\n---\n\n# Voiceover\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\n\nStart with the words, their pronunciation and the listening context. Fit the delivery to the meaning before optimizing duration.\n\nRead `./references/production.md` for fixed-window takes, a continuous measured story read,\nor an existing video plus photo becoming an on-screen narrator. These are distinct modes\nwith different timing/retry contracts; ordinary TTS and native UGC speech do not inherit\nthem automatically. Preserve voice locks and accepted takes; report missing revoice or\ncompositing capability instead of substituting a static portrait.\n\n## Make The Takes\n\n- Preserve the accepted text and speaker language. Choose a voice using the current CLI voice catalog; use real returned IDs. A stored voice ID is not evidence of voice-cloning support.\n- Split at natural thought or breath boundaries. Keep continuous passages together when tone matters; one subtitle per TTS request is only useful for a deliberately timed take list.\n- Use the voice model's actual supported controls for speed, emotion or style. Send the spoken text separately from nonspoken direction; do not accidentally speak labels such as “pause” unless the engine supports an established markup syntax.\n- Submit via the existing paid queue contract. Measure returned duration and listen for word errors, clipped ends and unnatural pauses.\n- If a time window is strict, record its bounds and actual voiced interval. Use the\n  selected mode's content/duration correction; never time-stretch or cut speech to fit.\n  A separately requested speed effect is an explicit edit, not a narration repair.\n\n## Cue Example\n\nSpoken text: “Open the lid, then press the button on the side.”\nDirection: reassuring instructional delivery; a natural breath after “lid”; pronounce every action clearly. Keep this direction outside the literal TTS text when the selected model has no markup/control for it.\n\n## Use With Video\n\nActual audio determines caption and edit timing. Use `../pixverse-captions/SKILL.md` when burned captions are requested. New narration over an on-camera speaker requires verified sync capability or a new native speech shot; do not silently replace the audio beneath old lip motion.\n\n## Deliver\n\nProvide the audio, exact spoken text, measured timing and take identifiers. Only repair failed takes. Avoid introducing a separate narration task where an accepted native video soundtrack already meets the brief.\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. Resolve the plugin root from this skill's installed path:\nset `PVX=\"<absolute-plugin-root>/scripts/pvx\"` and invoke `\"${PVX}\"` with the documented arguments.\nPrompt-only work ends with the usable plan and prompts; it needs no account or generation calls.\n"
}