How do I combine two voices equally?

Simply use the command 'blend [Voice A] and [Voice B]' to create a 50/50 mix of all tonal dimensions, vocabulary, and structural patterns.

What happens if I blend three or more voices?

The skill performs a multi-voice blend by averaging dimensions and merging vocabulary across all source profiles equally (e.g., 33.3% each for three voices).

Where are the blended profiles stored?

By default, blended profiles are saved as YAML files in your project's .aiwg/voices/ directory, but they can also be saved globally or to custom paths.

Can I set specific percentages for each voice?

Yes, the skill supports weighted blends. You can specify exact ratios like '80% technical-authority, 20% casual-conversational' for precise stylistic control.

Voice Profile Blender

Name: Voice Profile Blender
Author: jmagly

byjmagly

•

内容管理

Creates hybrid AI personas by merging multiple voice profiles using weighted interpolation and vocabulary reconciliation.

关于

Voice Profile Blender is a specialized utility for Claude Code that allows users to synthesize nuanced communication styles by mixing existing voice templates. It goes beyond simple concatenation by mathematically interpolating tone dimensions like formality and warmth, merging vocabulary preferences, and resolving structural patterns based on weighted dominance. This skill is ideal for developers and content creators who need to fine-tune an AI agent's personality—such as creating a persona that is 70% technical expert and 30% friendly guide—to ensure the AI communicates with the perfect balance of authority and accessibility.

主要功能

Dominant-voice structural resolution for consistent sentence and paragraph length
Automated interpolation of tonal dimensions including formality, confidence, and warmth
Weighted voice mixing with precise percentage control
Multi-source profile loading from templates, project files, and global configurations
Intelligent vocabulary merging with deduplicated preference lists
67 GitHub stars

使用场景

Creating a 'Friendly Expert' persona for developer documentation
Blending executive-level brevity with casual conversational styles for team reporting
Generating unique brand-aligned voices for autonomous agentic coding workflows

关于

主要功能

Dominant-voice structural resolution for consistent sentence and paragraph length
Automated interpolation of tonal dimensions including formality, confidence, and warmth
Weighted voice mixing with precise percentage control
Multi-source profile loading from templates, project files, and global configurations
Intelligent vocabulary merging with deduplicated preference lists
67 GitHub stars

使用场景

Creating a 'Friendly Expert' persona for developer documentation
Blending executive-level brevity with casual conversational styles for team reporting
Generating unique brand-aligned voices for autonomous agentic coding workflows