voice-casting

Select narration voice variants for each clip in family-based TTS workflows.

Updated May 23, 2026

Search Tags:#audio production #tts #narration #voice casting #show sidekick #clip segmentation

Ready to run

npx skills add https://github.com/spindle79/show-sidekick-narrative-pack --skill voice-casting

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice-casting
Source: https://github.com/spindle79/show-sidekick-narrative-pack/tree/main/packs/narration-voice/skills/voice-casting
Command: npx skills add https://github.com/spindle79/show-sidekick-narrative-pack --skill voice-casting

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Voice-casting helps you choose the best narration variant for each clip in a family-based TTS workflow, so mixed-register scripts sound natural instead of flat or mismatched.

Core Features & Use Cases

Per-clip variant selection: Picks neutral, warm, dynamic, or phonetic delivery based on the text in each clip.
Family-based voice control: Works when the user provides a voice family and the skill assigns the correct sibling variant for each line.
Narration planning: Produces casting decisions that fit Show Sidekick narration workflows, including problem-solution structure, direct address, and pronunciation-heavy segments.
Use Case: A script that opens with a hook, shifts into explanatory exposition, and ends with a technical model name can be split and cast with different variants so each beat lands correctly.

Quick Start

Use voice-casting to turn your narration script into a clip-by-clip casting plan for the voice family the user provided.

Frequently Asked Questions about voice-casting

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

FAQPage Schema

How do I choose the right TTS voice variant for different script sections?▼

Voice casting selects the right TTS voice variant for each script section by matching text register—like openers or direct address—to the correct sibling voice in a family, ensuring narration sounds natural instead of flat.

What is voice casting in a family-based TTS narration workflow?▼

Voice casting in a family-based TTS workflow assigns the correct sibling voice variant to individual narration clips based on their text, allowing mixed-register scripts to use different delivery styles like warm, dynamic, or phonetic.

How do I split a narration script into clips for TTS voice selection?▼

You split a narration script into mixed-register clips—such as hooks, explanatory exposition, and pronunciation-heavy lines—then voice casting assigns the appropriate family-based voice slug to each segmented clip.

Can I use voice casting for scripts with technical model names and pronunciation-heavy lines?▼

Yes, voice casting handles pronunciation-heavy lines by selecting a phonetic delivery variant, ensuring that technical model names and complex segments in your narration script land correctly.

What metadata do I need for TTS clip segmentation and voice casting?▼

You need brand guidance, section-level segmentation, family-specific voice slugs, and metadata output that preserves stable section IDs and clip-level casting decisions for the workflow to function correctly.

When should I use per-clip voice variant selection instead of a single TTS voice?▼

Use per-clip voice variant selection when a script shifts between narrative beats, such as moving from a hook to explanatory exposition, requiring different delivery variants so each beat lands correctly instead of sounding mismatched.