A skill that turns a file, web address, or topic into a short audio conversation between two hosts, then plays it through a local Voicebox server. It follows the style of NotebookLM Audio Overviews, which present source material as spoken discussion.

Making and playing spoken summaries of documents, web pages, or topics through the `/podcast` command and a Voicebox service.

It lets you listen to an overview instead of reading the source directly, while keeping the processing and playback on the local computer.

podcast — Skill for Claude Code and Codex by danylo-dudok/vocald

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add danylo-dudok/vocald --skill podcast-skill

Clone the repo

git clone --depth 1 https://github.com/danylo-dudok/vocald

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/danylo-dudok/vocald/podcast-skill/github.svg)](https://agentmods.dev/skills/danylo-dudok/vocald/podcast-skill)

Your own site

<a href="https://agentmods.dev/skills/danylo-dudok/vocald/podcast-skill"><img src="https://agentmods.dev/badge/skills/danylo-dudok/vocald/podcast-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/danylo-dudok/vocald/podcast-skill"><img src="https://agentmods.dev/badge/skills/danylo-dudok/vocald/podcast-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,149 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00066	$0.01149
Opus 5.5	$0.00026	$0.00460
Sonnet 5.5	$0.00013	$0.00230
Haiku 4.5	$0.00007	$0.00115

Measured 2mo ago against content hash 028efa44b8cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

podcast scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/say.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/podcast-skill/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuration (optional) — preferred voice profile names, if you have them: HOST_A = Bella (curious co-host, asks) · HOST_B = Alloy (expert, explains). Both are kokoro presets. If they don't exist, the skill auto-picks two profiles. Requires a running voice server on 127.0.0.1:17493 (default) — either vocald (headless: docker or brew-installed vocald-server) or the Voicebox desktop app. For a remote or authed vocald, export VOICEBOX_API=<base url> and VOICEBOX_API_KEY=<key> before running. macOS (afplay).

podcast — local NotebookLM-style audio overviews

Turn the given source into a short two-host audio conversation and play it aloud via vocald/Voicebox. Like NotebookLM's Audio Overview — no cloud, no upload, no leaving the terminal.

Two phases: write the entire script first, then voice it. Never interleave writing and speaking — compose the whole episode up front so it's coherent, then render it turn by turn.

How you are invoked

The user called you with a file path, a URL, or a topic, e.g.:

/podcast raw/some-article.md
/podcast https://example.com/post
/podcast the tradeoffs between Delta Lake and Iceberg

Steps

Pick the two voices. Call list_profiles (voicebox MCP tool, or GET $VOICEBOX_API/profiles — add Authorization: Bearer $VOICEBOX_API_KEY if the server enforces auth). If no profiles exist on a vocald server, create two kokoro presets first via the create_profile MCP tool (e.g. af_bella, af_alloy).
- Use the Configuration names (HOST_A / HOST_B) if present; otherwise the first two distinct profiles — and tell the user which two. Note the profiles' engine (the helper defaults to kokoro).
- Fewer than two profiles and create_profile unavailable (desktop app)? Stop and ask the user to create two in Voicebox → Voices, then rerun.
Get the source.
- File path → read it with the Read tool.
- URL → fetch it with WebFetch.
- No argument → use the current conversation, or ask what the podcast should be about.

Read the full file on GitHub · 72 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/say.sh 2.3 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 72 lines · 66 tokens per session scan A 028efa44b8cb

Subscribe to this mod's changes

podcast is a skill published in the GitHub repository danylo-dudok/vocald (0 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,149 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Creative and media

podcast next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
podcastdanylo-dudok/vocald	Skill	0	4mo ago	MIT	A	66	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	yesterday	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	100k	yesterday	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	5d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code