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 | "end-to-end audio", "speech generation", "image to audio", "image to audio generation", "multi-timbre dialogue", "reference audio cloning", "voice cloning", "sound effects", "generate sound effects" | /listenhub-voice |
| Podcast | "podcast", "podcast", "debate", "dialogue" | /podcast |
| Explainer video | "explainer", "explainer video", "tutorial video" | /explainer |
| Slides / PPT | "slides", "slides", "PPT", "presentation" | /slides |
| TTS / Read aloud | "TTS", "read aloud", "read aloud", "voiceover", "speech synthesis" | /tts |
| Image generation | "generate image", "draw one", "generate image", "AI image" | /image-gen |
| Video generation | "video", "video", "seedance", "pixverse", "generate video", "text to video", "make video", "lip sync", "lipsync", "lip sync" | /video-gen |
| Music | "music", "music", "generate music", "cover", "mix", "remix", "extend", "extend", "instrumental", "instrumental", "soundtrack", "soundtrack", "stem", "stem", "recognize lyrics", "clone vocals", "vocal clone" | /music |
| Content extraction | "parse URL", "extract content", "parse link" | /content-parser |
| Audio transcription | "transcribe", "ASR", "speech to text" | /asr |
| Creator workflow | "creation", "write WeChat official account", "Xiaohongshu", "spoken presentation" | /creator |
How to Route
- Read the user's message and identify which category it falls into
- Tell the user which skill you're routing to
- 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
- "Podcast" — Audio discussion on a topic
- "Explainer Video" — Narrated video with AI visuals
- "Slides" — Slide deck / presentation
- "Music" — AI music: generate, remix, instrumental, soundtrack, stem, vocal clone
- "Video" — AI video generation from text or reference materials
Prerequisites
Most skills require the ListenHub CLI. Check:
listenhub auth status --json
If not installed or not logged in, handle automatically — never ask the user to run install commands:
- Auto-install: run
npm install -g @marswave/listenhub-clisilently - Auto-login: run
listenhub auth login(opens browser)
Exception: /asr runs locally and needs no CLI or API key.