Update to Voyager Video & 3D

{
  "description": "Cloud: generate narration with premade or existing Voyager voices, music and sound effects.",
  "included_files": [],
  "name": "voyager-cloud-audio",
  "skill_md_contents": "---\nname: voyager-cloud-audio\ndescription: \"Cloud: generate narration with premade or existing Voyager voices, music and sound effects.\"\n---\n\n# Speech, music and sound effects\n\nFollow `voyager-cloud` (read it with `load_skill` if it isn't loaded) for account,\nmodels, costs and jobs. Audio jobs run\nin the background: poll `get_job` and present the player and download when done.\n\n## Narration\n\n1. `list_voices` lists premade voices. Choose one that fits the script's audience\n   and tone, or the voice the user names; offer two or three when the voice is\n   open and it matters.\n2. `list_voices` with `source` set to `mine` lists the user's existing cloned\n   voices when their plan includes voice cloning. This plugin never creates,\n   records or re-records a voice clone; if the user wants one, say it is made in\n   the Voyager app, where they give their own consent.\n3. Write the script for the ear: short sentences, numbers and names written as\n   spoken. Then `generate_speech` with the text, voice and the\n   speech model chosen as `voyager-cloud` describes.\n4. Listen-check claims honestly: report what you heard only if you could check it.\n\n## Direct the delivery\n\n- Emotion written as narration (\"she said sadly\") is spoken aloud. Direct delivery\n  with the markup the chosen speech model supports, such as bracketed tags\n  (`[whispering, playful]`), only where `list_models` or the model's description\n  says it accepts them; otherwise write the line so its wording carries the tone.\n- Ellipses add a pause and weight; capitals add emphasis. Don't use SSML.\n- Delivery works best when the voice already has it; a calm narrator will not\n  shout well.\n\n## Music\n\nDescribe genre, tempo, instruments, mood and structure in the prompt, and whether\nit is instrumental (a bed under speech or picture should be). Narrate the\narrangement (\"start with just piano, then bring in drums\"). Never ask for a\nparticular song's melody, lyrics or an artist's voice. Exact cue timing is never\nguaranteed. Call `generate_music` with a duration that fits the\nuse and the limits `list_models` reports for the chosen model.\n\n## Sound effects\n\n- One sound per prompt. Write a short sequence in order (\"footsteps on gravel,\n  then a metal door opens\"); make longer scenes as several cues.\n- Name the sound's kind: impact, whoosh, ambience, one-shot, loop, braam, glitch,\n  drone, plus tempo and key for musical hits.\n- Set a duration or looping only when `list_models` reports that setting and its\n  range for the model; otherwise let the model choose.\n- Deliver the format the job returns and name it in your reply; this plugin does\n  not convert or mix audio.\n\nGenerate each cue with `generate_sound_effect`, named by cue (`reveal-hit`,\n`ui-click-01`), and list the delivered files with their intended cue times.\n"
}