Overview
What is ListenHub MCP Server?
It is the official MCP server for ListenHub, enabling AI podcast generation (single or dual-speaker), FlowSpeech voice creation, and speaker and account management. It is available for ListenHub Pro plan and above.
How to use ListenHub MCP Server?
Requires Node.js 18+. Obtain an API key from the ListenHub API Keys settings page, then configure an MCP client (e.g., Claude Desktop, Cursor, Windsurf) using npx -y @marswave/listenhub-mcp-server@latest with the LISTENHUB_API_KEY environment variable. Alternatively, run in HTTP mode with --transport http --port 3000.
Key features of ListenHub MCP Server
- Full or text-only podcast generation with 1–2 speakers
- Multiple generation modes: Quick Listen, Deep Exploration, Debate
- Two‑stage generation and URL/text content sources
- FlowSpeech single‑speaker conversational audio from text or URLs
- Browse and filter speakers by language, gender, and attributes
- Query account subscription, credit usage, and renewal status
Use cases of ListenHub MCP Server
- Generate a podcast with one or two speakers from a topic or URL
- Create a FlowSpeech audio file from written content
- Manage available voices and check speaker details
- Monitor subscription credits and account status
FAQ from ListenHub MCP Server
What are the runtime dependencies?
Node.js version 18 or higher is required. No other runtime dependencies are mentioned.
How do I obtain an API key?
Get your API key from the ListenHub API Keys Settings page. Set it as the LISTENHUB_API_KEY environment variable.
What transport modes are supported?
Stdio mode (default) and HTTP mode (supporting HTTP streaming and Server‑Sent Events) are available.
Is there a free tier or plan requirement?
The server is available for ListenHub Pro plan and above.
Can the server generate audio from URLs?
Yes, both podcast and FlowSpeech generation can use text or URL content sources.
