A sophisticated workflow that transforms scripts into high-quality audiobooks, podcasts, or educational content using AI narration and ElevenLabs synthesis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install audio-gen
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install audio-gen using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Audio Content Generator?
The Audio Content Generator is a professional-grade tool within the Openclaw Skills ecosystem designed to bridge the gap between text-based ideation and high-fidelity audio production. By integrating Claude AI for creative scripting and ElevenLabs for industry-leading text-to-speech synthesis, this skill enables users to produce polished audio assets for storytelling, marketing, and e-learning. It handles complex narrative requirements, including emotional tone modulation and precise pacing, to ensure the output sounds human-centric rather than robotic.
This skill is particularly valuable for creators looking to scale their content production without investing in expensive recording equipment or voice talent. It automates the technical aspects of audio engineering, such as word-count-to-duration calculations and the application of SSML-style voice effects, allowing users to focus entirely on the core message and creative direction of their Openclaw Skills projects.
Audio Content Generator Use Cases
- Creating serialized audiobooks with dramatic pacing and emotional character voices.
- Producing recurring podcast episodes for brand updates or topical news summaries.
- Generating educational audio guides that break down complex technical subjects into digestible lessons.
- Developing narrated versions of existing blog posts or documentation for better accessibility.
- Building multi-part audio series for immersive storytelling or training modules.
How Audio Content Generator Works
- The skill analyzes the user's prompt to identify the content format (audiobook, podcast, or educational) and the desired duration.
- It calculates the target word count using a standard conversational ratio of approximately 75 words per minute.
- The agent generates a structured script including specific voice markers like
[short pause]and[excited]to guide the narration engine. - The user reviews the draft script and can request revisions for tone, length, or specific content details.
- Once approved, the system cleans the script of markdown and processes it through the ElevenLabs multilingual V2 model.
- The resulting MP3 file is stored in a temporary directory and returned to the user via a MEDIA token for immediate playback.
Audio Content Generator Setup
To use this skill within your Openclaw Skills environment, ensure your API keys are configured in your environment variables:
export ANTHROPIC_API_KEY="your_anthropic_key"
export ELEVENLABS_API_KEY="your_elevenlabs_key"
The skill relies on a Python-based TTS utility located in the sag skill directory. You can verify the installation by checking the path:
ls ~/.clawdbot/clawdbot/skills/sag/scripts/tts.py
Audio Content Generator Data Schema & Taxonomy
The skill organizes generated assets in a structured temporary filesystem to ensure performance and privacy.
| Property | Detail |
|---|---|
| Storage Location | /tmp/audio-gen/ |
| File Naming | audio-gen-[timestamp]-[topic-slug].mp3 |
| Audio Encoding | MPEG Layer-3 (MP3) |
| Default Model | eleven_multilingual_v2 |
| Retention | Automatic deletion after 24 hours |
Audio Content Generator Advanced Features
- Strategic use of voice modulation tags including
[whispers],[shouts], and[serious]for high-impact narration. - Precise pacing control through
[short pause]and[long pause]markers for natural breathing and transitions. - Support for specific ElevenLabs voice IDs to maintain a consistent brand persona across different audio files.
- Intelligent script length management that suggests condensing or expanding content to hit exact timing targets.
- Multi-episode workflow support for generating long-form content exceeding the 30-minute single-file limit.
SKILL.md
Loading
Related Openclaw Skills
DeepRead OCR & Structured Data Extraction
DeepRead is a production-grade OCR API that extracts structured JSON data from PDFs with AI-powered confidence scoring to minimize human review.
DeepRead
DeepRead is an AI-native OCR platform that turns documents into high-accuracy structured data using multi-model consensus and automated human-review flagging.
UCTOO API Integration Skill
An advanced Openclaw Skills integration that translates natural language into UCTOO backend API requests with automated token management.
UCM: API Marketplace for AI Agents
A comprehensive API marketplace that empowers AI agents to perform external tasks like web searching, image generation, and code execution through a single unified interface.
Clawdbot Sync
A robust synchronization utility for maintaining consistent memory, user profiles, and skills across multiple distributed AI agent instances.
Device Assistant
A comprehensive personal device and appliance manager that automates maintenance tracking and provides instant error code troubleshooting.
Featured*
