audio-cog

Generate voiceovers and music from scripts with customizable voices and MP3 export.

6|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/CellCog/cellcog_python --skill audio-cog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audio-cog
Source: https://github.com/CellCog/cellcog_python/tree/main/skills/audio-cog
Command: npx skills add https://github.com/CellCog/cellcog_python --skill audio-cog

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Create professional AI-generated audio content from scripts without requiring expert audio production skills, saving time and resources.

Core Features & Use Cases

  • Text-to-speech and voiceover generation using a spectrum of voices (cedar, marin, ballad, coral, echo, sage, shimmer, verse) with adjustable tone, pace, and emotion.
  • Music generation and sound design to produce background tracks, intros, and sonic branding with controllable duration, genre, tempo, mood, and instruments.
  • Output options and multilingual support for global audiences, including exportable MP3 audio files and cross-language prompts.

Quick Start

Provide a full script, preferred voice, and mood to generate the audio output.

Frequently Asked Questions about audio-cog

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

FAQPage Schema
How do I generate AI voiceovers from a script?

To generate AI voiceovers, provide a full script, select a preferred voice like cedar or marin, and specify a mood. The system processes the text to create professional voiceovers with adjustable tone, pace, and emotion.

Can I customize the accent and pacing for text-to-speech audio?

Yes, text-to-speech audio supports extensive voice customization. You can adjust accent, emotion, and pacing across multiple voices including ballad, coral, echo, sage, shimmer, and verse for tailored audio output.

What is the best way to create background music with specific tempo and mood?

The best way to create background music is using AI music generation by specifying desired duration, genre, tempo, mood, and instruments. This produces custom sound design tracks suitable for intros and sonic branding.

Does AI audio generation support multilingual prompts and MP3 export?

AI audio generation supports multilingual prompts for global audiences and exports cross-language audio content. You can output generated voiceovers and music directly as MP3 files for immediate use in projects.

Do I need expert audio production skills to create podcast intros?

No, you do not need expert audio production skills to create podcast intros. The AI generates professional audio content directly from scripts, saving time and resources for marketing, education, and media projects.

When should I use AI sound design instead of manual audio production?

Use AI sound design when you need professional audio content from scripts without expert production skills. It efficiently generates voiceovers, music, and ambient sounds, saving time and resources for marketing and media projects.