narratelisted

Turn a short written brief into a single-voice audio narration (MP3) you can listen to on a walk or commute, using the local Kokoro TTS from the voicemode plugin. Reusable engine — given already-condensed spoken text, it renders the MP3, saves it, and delivers it to the phone/desktop. Use when a command wants an audio version of an explanation (e.g. /handoff --audio, /wrap --audio) or when the user asks to "listen to" / "make audio of" a summary, brief, or recap. Triggers on "narrate", "audio version", "read it to me", "make an MP3 of this".
ksdisch/claude-config · ★ 0 · AI & Automation · score 73

Install: claude install-skill ksdisch/claude-config

# narrate — written brief → single-voice MP3 (local Kokoro) The reusable audio engine behind `/handoff --audio`, `/wrap --audio`, and any future command that wants a listenable explanation. **Local Kokoro only** (via the `voicemode` plugin): free, repeatable, no quota, no network. Single voice, narration — not a NotebookLM two-host podcast. NotebookLM cannot perform a script verbatim; this can, which is the whole point. **Engine, not author.** The *caller* decides what to say and hands this skill a clean spoken script. This skill renders it, saves it, and delivers it. If a caller hands you a raw artifact instead of a script, condense it first using the "Writing for the ear" rules below. --- ## Inputs (from the caller) - **`script`** — the text to speak, already written for the ear (see rules below). - **`voice`** — Kokoro voice id; default `am_adam`. Other common ids: `af_bella` (female), `bm_george` (male). Override per call or via `NARRATE_VOICE`. - **`out`** — desired MP3 path. If the caller doesn't give one, default to `~/Projects/_audio/<ISO-date>-<slug>.mp3` (create the dir). When narration accompanies a saved artifact (e.g. a `/wrap` log), prefer saving the MP3 next to it with the same basename so the pair stays together. - **`deliver`** — whether to `SendUserFile` the result (default yes). --- ## Workflow ### 1. Pre-flight — ensure Kokoro is up Load the voice tool (deferred): `ToolSearch` → `select:mcp__plugin_voicemode_voicemode__service`. Then `servic