
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.
- GitHub stars
- 293
- last updated
- Jun 9, 2026
Install
$ npx -y skills add utopai-research/pai-pro --skill voice-compose --agent claude-codeInstalls into .claude/skills of the current project.
Files
Default to one short reusable timbre sample per speaking character and one VO/narrator sample when narration exists. video-compose keeps actual shot dialogue/VO in the video prompt. Treat audio_result.data.text as downstream speech only for approved final narration/line reads.
Patterns
Follow PROJECT_AGENT.md for context/staging. This skill owns voice prompt + CLI shape.
1. Character voice sample
Triggers: "give / design a voice for [character]", "what does [character] sound like", "voices for all the characters on the canvas".
- Target: any
image_resultfor the person; don't gate on subtype. Readdata.local_pathbefore prompt; layername/role/descriptionon top. - Call:
node "$PAI_REPO_ROOT/server/cli/generate_voice.js" \ --text "<line>" \ --prompt "<voice design brief>" \ --source-node-id <character.id> - Prompt describes the voice, not the character:
[age bracket] [gender], [timbre], [register], [pace], [accent if relevant]. [optional emotional color].
Sponsors
Details
- Repository
- github.com/utopai-research/pai-pro
- Categories
- Data Science & ML, Mobile Development, CLI & Terminal
- First seen
- Jun 11, 2026