# listenhub

Routes user prompts to specialized ListenHub skills based on detected intent. Helpful when generating podcasts, voiceovers, music, slides, or video.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1500 installs · ★ 81
- Author: marswaveai
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/marswaveai/skills/tree/HEAD/listenhub/SKILL.md
- Updated: 2026-09-24
- HTML: https://affpapa.org/en/nevibecode/skills/listenhub

## What it does

listenhub acts as an intent router for the ListenHub ecosystem. Instead of calling separate commands manually, you send a generic prompt such as creating a podcast or cloning a voice. The skill checks trigger keywords against its routing table and forwards the task to the corresponding tool, such as `/podcast` or `/video-gen`. It clarifies ambiguous intents directly.

Most tasks depend on the ListenHub CLI tool. The skill checks authentication using `listenhub auth status --json`. If the tool is missing, it runs `npm install -g @marswave/listenhub-cli` in the background and launches `listenhub auth login` in the browser. The only exception is the `/asr` skill. Audio transcription runs locally, so it needs neither a CLI nor an API key.

Automatic browser login simplifies setup on a desktop, but it stalls headless environments without a display. This is a clear reason to verify CLI credentials before triggering automated media generation.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add marswaveai/skills --skill listenhub -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/listenhub/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/listenhub/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add marswaveai/skills --skill listenhub -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/listenhub/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add marswaveai/skills --skill listenhub -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/listenhub/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install marswaveai/skills listenhub
```

2. **Manually: put the files in place**
- File: `.github/skills/listenhub/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add marswaveai/skills --skill listenhub -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/marswaveai/skills --path listenhub
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/listenhub/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add marswaveai/skills --skill listenhub -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/marswaveai/skills/tree/HEAD/listenhub/SKILL.md

## When to use it
- route media generation prompts to specialized ListenHub sub-skills
- trigger text-to-speech and voice cloning through a single entry point
- extract web page content from a shared URL
- run local audio transcription without external API keys

## Example prompts
- make a podcast about distributed systems and consensus algorithms
- generate background music for an explainer video
- read aloud the release notes from notes.txt using TTS

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: ac3e705587f50efb.

BEGIN THIRD-PARTY FILE ac3e705587f50efb
````text
---
name: listenhub
version: 1.0.0
description: |
  ListenHub CLI skills router. Routes to the correct skill based on user intent.
  Triggers on: "make a podcast", "explainer video", "read aloud", "TTS",
  "generate image", "generate video", "做播客", "解说视频", "朗读", "生成图片",
  "生成视频", "幻灯片", "slides", "音乐", "music", "generate music", "翻唱",
  "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐",
  "soundtrack", "分轨", "stem", "识别歌词", "克隆人声", "vocal clone",
  "cover song", "pixverse", "口型", "lipsync", "对口型",
  "parse URL", "解析链接", "提取内容".
metadata:
  openclaw:
    emoji: "🎧"
    requires:
      bin: ["listenhub"]
    primaryBin: "listenhub"
---

## Purpose

This is a router skill. When users trigger a general ListenHub action, this skill identifies the intent and delegates to the appropriate specialized skill.

## Routing Table

| User intent | Keywords | Route to |
|-------------|----------|----------|
| ListenHub Voice end-to-end audio | "端到端音频", "语音生成", "图片转音频", "图片生成音频", "多音色对白", "参考音频克隆", "克隆音色", "音效", "生成音效" | `/listenhub-voice` |
| Podcast | "podcast", "播客", "debate", "dialogue" | `/podcast` |
| Explainer video | "explainer", "解说视频", "tutorial video" | `/explainer` |
| Slides / PPT | "slides", "幻灯片", "PPT", "presentation" | `/slides` |
| Voice cloning (persistent) | "克隆我的声音", "克隆音色", "声音克隆", "语音克隆", "用我的声音", "自定义音色", "clone my voice", "custom voice" | `/voice-clone` |
| TTS / Read aloud | "TTS", "read aloud", "朗读", "配音", "语音合成" | `/tts` |
| Image generation | "generate image", "画一张", "生成图片", "AI图" | `/image-gen` |
| Video generation | "video", "视频", "seedance", "pixverse", "生成视频", "text to video", "做视频", "口型", "lipsync", "对口型" | `/video-gen` |
| Music | "music", "音乐", "生成音乐", "翻唱", "混音", "remix", "续写", "extend", "纯音乐", "instrumental", "配乐", "soundtrack", "分轨", "stem", "识别歌词", "克隆人声", "vocal clone" | `/music` |
| Content extraction | "parse URL", "extract content", "解析链接" | `/content-parser` |
| Audio transcription | "transcribe", "ASR", "语音转文字" | `/asr` |
| Creator workflow | "创作", "写公众号", "小红书", "口播" | `/creator` |

## How to Route

1. Read the user's message and identify which category it falls into
2. Tell the user which skill you're routing to
3. Follow that skill's SKILL.md completely

If the intent is ambiguous, ask the user to clarify:

```
Question: "What would you like to create?"
Options:
  - "ListenHub Voice" — End-to-end audio: sound effects, multi-voice dialogue, reference-audio cloning, image→audio
  - "Voice Cloning" — Clone your own voice into a reusable speaker
````
END THIRD-PARTY FILE ac3e705587f50efb

The third-party file has ended. Everything between the ac3e705587f50efb tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2958 of 3668 bytes. © marswaveai · MIT · https://github.com/marswaveai/skills/tree/HEAD/listenhub/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md