What voice engines does the Audio Producer Agent support?

The skill supports multiple high-quality engines including Gemini TTS, ElevenLabs, and OpenAI TTS for diverse narration styles.

How does the skill handle very long text files?

The agent can split long-form content into manageable chunks or chapters to stay within engine token limits and then concatenate them into a final file.

Does it include background music capabilities?

Yes, it utilizes Google’s Lyria model to generate custom background music or ambient soundscapes that are automatically mixed with the narration.

What are the technical prerequisites for using this skill?

You will need a valid GOOGLE_API_KEY for audio generation and FFmpeg installed on your local machine to handle audio assembly and mixing.

Can I create podcast-style conversations with this skill?

No, this skill is specifically optimized for single-voice content. For dialogues or multi-speaker shows, you should use the podcast-producer skill instead.

Audio Producer Agent

Name: Audio Producer Agent
Author: michaelboeding

bymichaelboeding

•

内容管理

Generates professional single-voice audio content, including narrations, voiceovers, and ads, with integrated background music and automated mixing.

The Audio Producer Agent is an advanced orchestration skill for Claude Code designed to streamline the creation of high-quality single-speaker audio projects. By integrating leading text-to-speech engines like Gemini or ElevenLabs with AI-driven music generation from Lyria and precise FFmpeg-based mixing, it allows users to transform raw text into polished audiobooks, energetic radio spots, or soothing meditation guides. The skill utilizes a structured, interactive workflow to capture specific requirements for voice style, pacing, and ambient density, ensuring professional-grade results directly from your development environment.

主要功能

01Long-form content processing with automated chapter concatenation

02Interactive requirement gathering for precise control over voice style and tone

039 GitHub stars

04Automated audio mixing with configurable volume, fades, and crossfades

05Multi-engine Text-to-Speech support including Gemini, ElevenLabs, and OpenAI

06AI-generated background music and soundscapes via Lyria integration

使用场景

01Producing 30-second radio advertisements or sonic logos with specific brand taglines

02Creating guided meditation sessions or audio tours with layered ambient soundscapes

03Converting manuscripts and articles into professional-grade audiobooks with consistent narration

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add michaelboeding/skills audio-producer-agent

For use in Claude.ai and ChatGPT

Download Skill