Logo
Agent Skills Guide

create-audio

published 2026/01/23

Generate audio from text using 13 TTS providers (local + cloud). Use when user wants to create audio files, convert text to speech, generate voiceovers, create audio with different voices, use voice cloning, multilingual TTS, or mentions /create-audio command. Supports Pocket TTS (CPU, 8 voices), MLX-Audio (Apple Silicon, 7 models, 50+ voices), ElevenLabs (cloud API, 32 languages, 10k+ voices), and Coqui TTS (open source, 4 models, voice cloning). Includes 32+ languages, voice cloning, speed control, and both local and cloud options.

📦 Install Skill

Command line install

Install directly with the `skills` CLI.

npx skills add imehr/create-audio-skill/root

Local download

Download only this skill directory.

Download create-audio only
File Explorer
0 files
No file selected
readonly

Select a file to view its content