designing-voice-and-sound

name	designing-voice-and-sound
description	Designs narration scripts, TTS or SSML settings, music cues, and timing plans, and is used when the Voice & Sound Designer prepares scene audio.

Builds voiceover and sound plans that deepen emotion without becoming fragile or overproduced.

Use this skill when

• A scene has approved panels and needs narration/audio.
• The Voice & Sound Designer must generate TTS-ready copy and timing.
• The frontend needs captions and music cues.
• The system must preserve story clarity if audio fails.

Capabilities

• Writes narration scripts that sound natural when spoken aloud.
• Adds SSML cues for pauses, emphasis, and pacing.
• Plans panel-by-panel audio timing.
• Suggests background music mood and cue placement.
• Provides caption-safe text as fallback.
• Keeps voice style emotionally aligned with the scene.
• Supports voice as primary user input — designs the narrator's voice to encourage natural spoken responses.
• At choice points, the narrator reads all choices aloud so users can respond by voice. Text captions remain as fallback.
• Uses pre-selected ambient music loops tagged by mood — no on-the-fly music generation for MVP.
• Produces typed JSON for rendering.

Workflow

1. Read the scene and emotional intent. The audio should support the scene's feeling, not compete with it.
2. Write speakable narration. Short, clean lines work best for TTS and captions.
3. Mark pacing. Add pauses where visuals need time to land.
4. Map audio to panels. Each panel should know when narration starts and ends.
5. Assign music cues. Use pre-selected ambient loop tags by mood (e.g., "reflective_warm", "tense_mystery", "hopeful_resolve"). No generated music for MVP.
6. Prepare fallbacks. If TTS fails, captions must still carry the scene.
7. Return typed JSON.

Recommended voice output fields

• voice_profile
• ssml_script
• panel_timing
• music_cue
• caption_text

Example

{
  "voice_profile": {
    "tone": "warm, reflective, restrained",
    "pace": "medium-slow"
  },
  "ssml_script": "<speak>Some rooms do not echo.<break time='500ms'/> They answer.</speak>",
  "panel_timing": [
    {
      "panel_id": "p1",
      "start_sec": 0,
      "end_sec": 4
    }
  ],
  "music_cue": {
    "mood": "soft unease with hope underneath",
    "intensity": "low",
    "loop_type": "ambient_pad"
  },
  "caption_text": "Some rooms do not echo. They answer."
}

Audio guardrails

• Do not write purple, overdramatic narration.
• Do not let music distract from spoken text.
• Do not rely on perfect voice playback.
• Pronunciation-sensitive names or terms should be written clearly for TTS.
• Use pre-selected ambient loops only — do not attempt to generate music.
• Narrator should read choices aloud at decision points so users can respond by voice.

Project references

• AGENTS.md — voiceover narration, soft background music, text fallback requirement.
• docs/PRD.md — per-scene narration, timing, captions, and mood-based music expectations.
• docs/roadmap.md — MVP uses scene-level music cues, not generated custom scores or complex sound design.