Voice Compose

Handles voice generation for filmmaking projects by wrapping the local generate_voice.js CLI. Two main modes: character voice samples that attach to existing character images on the canvas and act as timbre anchors for downstream video dialogue, or standalone narration and VO tracks. The skill reads character images first to ground voice descriptions in what it actually sees, then constructs prompts that describe sound qualities like timbre, register, and pace rather than character traits. Everything routes through a staging gate so you review drafts before committing audio nodes to the canvas. Useful when you need consistent character voices across a script without generating every single line as final audio, or when you want narrator tracks that carry exact line reads.

Install to Claude Code

npx -y skills add utopai-research/pai-pro --skill voice-compose --agent claude-code