skills.rest
anymouschina
anymouschinaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

voice-performance-director

Converts dialogue and character states into executable voice acting performance instructions.

590|153|Updated Nov 11, 2025
Search Tags:#character voice#narration#voice acting#dubbing#performance direction#audio drama#dialogue annotation
One-click install
npx skills add https://github.com/anymouschina/TapCanvas --skill voice-performance-director
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-performance-director
Source: https://github.com/anymouschina/TapCanvas/tree/main/apps/hono-api/marketplace-skills/voice-performance-director
Command: npx skills add https://github.com/anymouschina/TapCanvas --skill voice-performance-director

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Translating abstract emotions like "sad" or "angry" into concrete, performable voice direction is hard for writers and directors. This Skill turns dialogue, narration, and character states into specific instructions covering breath, pace, stress, pauses, and subtext that voice actors can directly execute.

Core Features & Use Cases

  • Line-by-line performance annotation: Marks breathing points, stressed words, speed changes, and unspoken intent for each line of dialogue.
  • Multi-character voice differentiation: Establishes a stable vocal baseline per character with scene-specific offsets, keeping roles distinguishable without stereotypes.
  • Consistency checking: Verifies turn-taking, interruptions, and silences match character relationships, and outputs an energy curve for the whole scene.
  • Use Case: A comic-drama production team feeds a scene's script into the Skill and receives per-line delivery directions plus open items requiring on-site director judgment before recording.

Quick Start

Annotate the dialogue in my script with voice performance directions including emotion, pacing, stress, and pauses for each character.

Frequently Asked Questions about voice-performance-director

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I annotate dialogue with voice acting directions?▼

Provide the script with scene context and character relationships. The Skill breaks dialogue into semantic units and marks breathing points, stressed words, speed changes, and subtext for each line, producing actor-ready performance instructions.

How to keep multiple character voices distinguishable in dubbing?▼

The Skill builds a stable vocal baseline per character using rhythm, register, articulation, and energy, then applies scene-specific offsets. It avoids stereotypes based on accent, gender, or age while keeping roles naturally distinct.

Can this Skill check dubbing consistency across a scene?▼

Yes. It reviews turn-taking, interruptions, and silences against character relationships, then outputs an energy curve for the whole scene plus consistency checkpoints for the recording session.

What are the limitations of automated voice direction annotation?▼

The Skill does not rewrite lines the user must keep and avoids defaulting to extreme delivery like shouting for strong emotions. It flags open items that still require on-site director judgment during recording.

Does voice performance annotation work for narration and voiceover?▼

Yes. Beyond character dialogue, it handles narration rhythm and pacing, translating the narrator's intent into concrete speed, pause, and emphasis instructions suitable for voiceover recording.

Related Skills

Explore More Content & Communication Skills→
MochocyangMochocyang
751

dialogue-emotion

Guides writing and revision of dialogue, subtext, and emotional beats in fiction.

Community
Basic
curiositechcuriositech
181

voice-audio-engineer

Generate speech with ElevenLabs and process audio to broadcast loudness standards.

Official
Advanced
Deland78Deland78
2

Act Outline

Generates annotated XML storyboards with embedded director's notes and generates PNG images of them.

Community
Advanced
cuba6112cuba6112

unsloth-tts

Fine-tune Orpheus-TTS models for voice cloning with Unsloth optimizations.

Community
Intermediate