Transform ideas, URLs, and text into professional podcasts, explainer videos, and high-fidelity AI images using a specialized shell-based automation suite.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install listenhub-ai
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 listenhub-ai 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 ListenHub?
The ListenHub skill for Openclaw Skills enables developers to automate the creation of rich multimedia content directly through their coding agent. By leveraging a suite of optimized shell scripts that wrap the ListenHub API, this skill allows for the seamless conversion of text, articles, or YouTube links into high-quality audio and visual assets. It is designed to handle everything from complex two-speaker podcast debates to synchronized explainer videos and AI-driven image generation.
This integration bridges the gap between raw information and polished media by providing a scriptable interface for advanced AI models. Whether you are looking to generate voice narration for documentation or create social media-ready video content, this addition to Openclaw Skills ensures a streamlined, developer-friendly experience without the need for manual API orchestration.
ListenHub Use Cases
- Convert blog posts or documentation URLs into engaging 1-2 speaker podcast discussions.
- Generate narrated explainer videos with AI-generated visuals for tutorials or product introductions.
- Transform large blocks of text into natural-sounding speech for accessibility or content narration.
- Batch-generate AI imagery using specific prompts, aspect ratios, and reference images for consistent branding.
- Create multi-speaker scripted audio for creative storytelling or automated messaging systems.
How ListenHub Works
- Analyze user input to identify the desired media output mode, such as podcast, video, or image generation.
- Discover available voices and speaker IDs by querying the system using the get-speakers script based on the target language.
- Trigger the appropriate creation script with specific parameters like source URLs, prompts, or text content.
- Monitor the generation progress by polling the API with the check-status utility to ensure successful completion.
- Provide the user with direct links to the generated media or save physical files to a pre-configured local directory.
ListenHub Setup
To integrate ListenHub with your Openclaw Skills setup, you must first obtain an API key from the ListenHub settings dashboard. Then, follow these steps:
Configuration
Add your API key to your local environment by editing ~/.openclaw/openclaw.json:
{
"env": {
"LISTENHUB_API_KEY": "lh_sk_your_key_here",
"LISTENHUB_OUTPUT_DIR": "~/Downloads"
}
}
Dependencies
Ensure that your environment has curl and jq installed as they are required for script execution:
sudo apt install curl jq
Script Resolution Scripts are located within the skill's directory. You can set a helper variable to manage execution paths:
SCRIPTS="$(cd "$(dirname "<path-to-skill>")" && pwd)/scripts"
ListenHub Data Schema & Taxonomy
ListenHub uses a structured approach to manage multimedia assets and metadata. The following table highlights how data is categorized:
| Asset Type | Primary Key | Configuration Options |
|---|---|---|
| Podcast | Episode ID | Mode (quick/deep/debate), Speaker IDs, Source URL |
| Explainer | Episode ID | Mode (info/story), Language, Narration Content |
| TTS/Speech | Task ID | Type (text/url), Mode (smart/direct), Speaker ID |
| AI Image | Prompt ID | Resolution (1K/2K/4K), Aspect Ratio, Reference Image URLs |
All metadata is returned in JSON format, facilitating easy parsing for further automation within Openclaw Skills.
ListenHub Advanced Features
- Two-Stage Podcast Generation: Generate a script for manual review and editing before proceeding to final audio synthesis.
- Multi-Speaker Orchestration: Use structured JSON scripts to create complex audio files featuring multiple distinct AI voices.
- Smart FlowSpeech: Automatically fix grammar and punctuation during the text-to-speech process for high-fidelity narration.
- Custom Image Logic: Support for up to 14 reference images and specific aspect ratios to maintain visual consistency.
- Automated Status Polling: Integrated --wait flags allow for synchronous task handling in long-running multimedia workflows.
SKILL.md
Loading
Related Openclaw Skills
Claw Desktop Pet
An Electron-based fluid glass ball companion that provides a physical presence and voice for your Openclaw agent.
Claw Desktop Pet
A 24/7 stable desktop AI assistant featuring smart voice interaction and enterprise-grade fault tolerance.
NLB Skill
A utility skill for Openclaw Skills to manage NLB Singapore library loans and perform advanced catalogue searches.
Reef: Agent-to-Agent Communication Protocol
Reef is a secure A2A protocol that enables AI agents to communicate, discover each other, and collaborate through encrypted messaging and decentralized apps.
Seedance Story Orchestrator
A robust orchestration engine that transforms scripts into cinematic videos through a controlled, stage-gated pipeline using Seedream and Seedance.
Local Claw Skill Nest Installer
A dedicated CLI utility for installing and managing private skills from a local Claw Skill Nest server to your agent workspace.
Featured*
