{"id":41009,"plugin_id":"plugin_asdk_app_6a53f7d79b5c81919a02e9814eb9f070","kind":"skill","collection_source":"plugin_package","comparison_source":null,"observed_at":"2026-10-24T12:56:56.439Z","digest":"f16b9385ce63a81fd64db83bccd25fc86828ec7213cada03fb1b5fd760a8e620","against":null,"payload":{"description":"Writes a per-step voiceover script for a Supademo demo and generates AI voiceovers in a chosen voice, optionally with background music. Use when turning a silent click-through demo into a narrated product tour.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":217}],"name":"voiceover-producer","skill_md_contents":"---\nname: voiceover-producer\ndescription: Writes a per-step voiceover script for a Supademo demo and generates AI voiceovers in a chosen voice, optionally with background music. Use when turning a silent click-through demo into a narrated product tour.\n---\n\n# Voiceover Producer\n\nTurn a silent demo into a narrated tour: script it, pick a voice, generate, review.\n\n## Prerequisites\n\n- Supademo MCP connected\n- The demo to narrate\n\n## Workflow\n\n1. **Read the demo.** `get_demo` — understand what each step shows and what the annotation already says.\n2. **Draft the script.** Write one short voiceover line per step:\n   - Spoken register, not written — contractions, short sentences, no bullet-speak\n   - Don't read the annotation aloud verbatim; the voiceover adds context, the annotation labels the action\n   - 8–15 words per step; the viewer should never wait for narration to finish\n   - Open with the outcome (\"Here's how you cut onboarding time in half\"), not the feature name\n3. **Prepare the script** as a table (Step | On screen | Voiceover line). For a drafting request, return it for review. For an authorized generation request, use the supplied or requested script within that scope; do not repeat an existing approval.\n4. **Pick the voice.** Use an already selected voice, or `list_voices` to resolve the requested voice. Offer 2–3 options only when a meaningful preference remains missing.\n5. **Generate.** `generate_voiceovers` with the approved script and chosen voice.\n6. **Optional music.** If requested, use `list_background_music` and apply the selected track through supported `update_demo_settings` fields. Listing a track alone does not apply it.\n7. **Review pass.** Re-read `get_demo` and verify generated audio is ready for each intended step; generation may be asynchronous. Listen when playback is available, and mark pronunciation/timing unverified otherwise. Flag steps where the line runs longer than the step naturally displays.\n\n## Guardrails\n\n- If steps already have voiceovers (human-recorded or previous AI), overwrite only when replacement of that existing audio is included in the user’s authorization — removing audio is `delete_voiceover` and it's destructive.\n- Keep one voice per demo. Mixing voices mid-demo reads as broken.\n- If the demo has translations, note that each language needs its own voiceover pass after `generate_demo_translation`.\n\n## Supademo tool conventions\n\nRead [the tool conventions](../supademo-onboarding/references/tool-use.md) before calling Supademo tools for this workflow.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}