ListenHub is a powerful content transformation tool that converts text, URLs, and ideas into high-quality podcasts, explainer videos, and AI-generated imagery.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install listenhub
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 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?
ListenHub serves as a bridge between raw information and multimedia output. By integrating these Openclaw Skills into your workflow, you can automate the production of two-person podcast dialogues, single-narrator explainer videos with AI visuals, and standard text-to-speech narrations. It simplifies complex API interactions into a set of streamlined shell scripts, allowing AI agents to generate professional audio and visual content without manual overhead.
The tool is designed for maximum flexibility, supporting inputs from plain text, web articles, and YouTube links. Whether you are looking to visualize a concept through image generation or turn a dry document into an engaging audio discussion, ListenHub provides the necessary infrastructure to do so within a developer-centric environment.
ListenHub Use Cases
- Transforming long-form articles or YouTube videos into digestible two-person podcast discussions.
- Generating professional explainer videos for product introductions or technical tutorials.
- Converting written documents or notes into high-quality voice narration for audio review.
- Creating AI-generated concept art and illustrations from text prompts or reference images.
- Automating multi-speaker dialogue scripts for storytelling or training materials.
How ListenHub Works
- The agent identifies the user's intent (e.g., "podcast", "explain", "visualize") to select the appropriate generation mode.
- If required, the agent retrieves available voice models using the speaker discovery script to match the target language and style.
- The agent executes a dedicated shell script (e.g., create-podcast.sh) passing the source text, URL, or prompt as arguments.
- The generation task is submitted to the ListenHub API, and an Episode ID is returned for tracking.
- The agent polls the status using the check-status script, often utilizing background execution or wait modes.
- Once complete, the agent provides the user with a web link to the generated media or a local path for downloaded files.
ListenHub Setup
First, ensure curl and jq are installed on your system. To configure the Openclaw Skills for ListenHub, follow these steps:
- Obtain your API key from https://listenhub.ai/settings/api-keys.
- Set the environment variables in your shell configuration file (e.g.,
~/.zshrc):
export LISTENHUB_API_KEY='your_lh_sk_...'
export LISTENHUB_OUTPUT_DIR='~/Downloads'
- Refresh your environment:
source ~/.zshrc
ListenHub Data Schema & Taxonomy
The skill manages several data types and metadata outputs during the generation lifecycle:
| Data Type | Format | Description |
|---|---|---|
| Podcast Draft | Markdown (.md) | A human-readable version of the podcast script for review. |
| Podcast Scripts | JSON (.json) | The machine-readable dialogue structure used for audio synthesis. |
| AI Images | JPG/PNG | Visual assets generated via prompts, saved to the output directory. |
| Task Status | JSON | Metadata containing Episode IDs, durations, and streaming URLs. |
ListenHub Advanced Features
- Two-stage podcast generation allowing for manual script review and editing before audio synthesis.
- Multi-speaker support for complex dialogue and script-based voice generation via create-speech.sh.
- Reference image support for image generation, allowing up to 14 URLs to guide visual style.
- Automated polling with the
--waitflag, including configurable timeouts, intervals, and retry logic. - Support for FlowSpeech direct mode to narrate content without altering original grammar or punctuation.
SKILL.md
Loading
Related Openclaw Skills
AIresearchOS
AIresearchOS is a deep research engine that enables users to submit complex queries and receive comprehensive, multi-source reports directly within an agent workflow.
Discord Chat
A comprehensive communication skill enabling AI agents to interact with Discord channels through messages, replies, reactions, and advanced history searching.
whalecli
An agent-native whale wallet tracker for monitoring large BTC and ETH movements and scoring smart money activity.
WEEX Futures Trading
A high-performance AI agent skill for executing USDT-margined perpetual futures trades on the WEEX exchange with up to 125x leverage.
Lark Calendar & Task Management
A powerful automation tool for managing Lark (Feishu) calendar events and tasks with built-in employee name resolution.
Lark & Feishu Integration
A robust webhook bridge that connects Lark or Feishu messaging platforms to OpenClaw for intelligent, bidirectional AI communication.
Featured*
