sanzaru: Command for Claude Code

.claude/commands/podcast-gen.md

podcast-gen is a command for Claude Code from TJC-LP/sanzaru. It costs 0 tokens per session (1,886 once invoked), scanned A, original, MIT.

A podcast-generation workflow that turns a structured script with multiple speakers into one downloadable MP3 or WAV file. It creates each spoken part with text-to-speech and joins them with configurable pauses.

In plain words
What is it for?
Use it to clarify an episode, write its script, estimate its length, and generate the finished audio file.
Why use it?
It removes the manual work of recording, combining, and timing separate voices for a podcast episode.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is TJC-LP/sanzaru's own configuration. It tells Claude Code how to work on sanzaru itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sanzaru configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TJC-LP/sanzaru. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TJC-LP/sanzaru/main/.claude/commands/podcast-gen.md
Clone the repo
git clone --depth 1 https://github.com/TJC-LP/sanzaru

Made for: Claude Code.

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.

agentmods badge for podcast-gen

README.md
[![agentmods](https://agentmods.dev/badge/commands/tjc-lp/sanzaru/podcast-gen/github.svg)](https://agentmods.dev/commands/tjc-lp/sanzaru/podcast-gen)
Your own site
<a href="https://agentmods.dev/commands/tjc-lp/sanzaru/podcast-gen"><img src="https://agentmods.dev/badge/commands/tjc-lp/sanzaru/podcast-gen/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.

agentmods 80×15 button for podcast-gen

Your own site · 80×15
<a href="https://agentmods.dev/commands/tjc-lp/sanzaru/podcast-gen"><img src="https://agentmods.dev/badge/commands/tjc-lp/sanzaru/podcast-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,886 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01886
Opus 5 $0.00000 $0.00943
Sonnet 5 $0.00000 $0.00377
Haiku 4.5 $0.00000 $0.00189

Measured 11d ago against content hash 51e539f81f4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

podcast-gen 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 11d ago.

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.

.claude/commands/podcast-gen.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are generating a multi-voice podcast using Sanzaru's generate_podcast tool.

Overview

The generate_podcast tool takes a structured PodcastScript and produces a single downloadable mp3 (or wav) file. It generates each spoken segment via TTS, then stitches them together with configurable silence gaps.

Step-by-Step Workflow

  1. Clarify the topic and format — confirm episode topic, number of speakers, desired tone, and approximate length before writing the script.

  2. Write the PodcastScript — produce the full script object (see schema below). Aim for natural conversational exchanges. 1–2 sentences per turn feels realistic.

  3. Estimate duration — count words in all segments, divide by (150 × avg_speed). A typical 10-minute podcast needs ~1500 words of spoken content.

  4. Call generate_podcast — pass the script. Generation takes time proportional to total word count (sequential TTS). Expect ~30–90 seconds for a 5–10 minute podcast.

  5. Deliver the file:

    • Always: the output_file is written to the audio directory — tell the user the filename.
    • Desktop: call view_media(media_type="audio", filename=<output_file>) to open the player, then tell the user the filename as backup.
    • Mobile / unknown: just report the filename and instruct the user to find it in their configured audio directory. Do NOT attempt view_media on mobile.
  6. Optional: share the transcript — the result includes a full formatted transcript. Offer to share or save it as show notes.


Voice Pairing Guide

Voice contrast is critical for listener comprehension. Pair voices with clear tonal differences so listeners can distinguish speakers without visual cues.

Recommended Pairings

Format Speaker A Speaker B Notes
News / analysis ash nova Ash: authoritative anchor; Nova: energetic reporter
Technical deep-dive onyx coral Onyx: measured, deep; Coral: enthusiastic
Interview fable alloy Fable: warm interviewer; Alloy: neutral subject
Debate ash shimmer Strong contrast between confident and smooth
Narrative / documentary onyx (narrator) fable (subject) Narrator separate from subject
3-way panel ash + nova + echo Good spread across pitch and energy

Read the full file on GitHub · 210 lines

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.

  1. 11d ago First seen · 210 lines · 0 tokens per session scan A 51e539f81f4b

Subscribe to this mod's changes

podcast-gen is a command published in the GitHub repository TJC-LP/sanzaru (6 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,886 tokens. 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.