characteristic-voice

Installation
Summary

Add human warmth, emotion, and natural speech patterns to AI voice output.

  • Includes five speaking presets (good night, good morning, comfort, celebration, just chatting) that automatically tune pace, warmth, and emotional tone
  • Sprinkle non-lexical fillers (hmm, aww, haha, sighs) at natural pauses to create conversational authenticity; supports up to 4 fillers per short message
  • Clone specific character voices by providing reference audio from YouTube clips or personal recordings, forwarded to the Noiz backend for voice matching
  • Customize emotional parameters (tenderness, joy, sadness) and speech speed independently via JSON emotion maps or use preset defaults
SKILL.md

characteristic-voice

Make your AI agent sound like a real companion — one who sighs, laughs, hesitates, and speaks with genuine feeling.

Credentials

Variable Required Description
NOIZ_API_KEY Yes if using Noiz backend API key from developers.noiz.ai. Not needed if using the local Kokoro backend.

The script saves a normalised copy of the key to ~/.noiz_api_key (mode 600) for convenience. To set it:

bash skills/characteristic-voice/scripts/speak.sh config --set-api-key YOUR_KEY

Prerequisites

The included speak.sh script requires curl and python3 at runtime. Depending on which backend and features you use, you may also need:

Related skills

More from noizai/skills

Installs
2.5K
Repository
noizai/skills
GitHub Stars
498
First Seen
Mar 1, 2026