podcast-production
Produce audio-first podcast episodes with generative tools — design the show and episode format (interview, narrative, news brief, two-host conversational), write scripts for the ear, decide between fully-synthetic and hybrid (recorded human + synthetic) production and meet the disclosure duty each triggers, cast and direct multi-voice TTS for consistency and chemistry, build episode structure (cold open, intro/outro, segments, ad slots), assemble and edit, clear music and SFX rights, hit podcast loudness and delivery standards, ship metadata/chapters/transcripts through RSS, and pass platf
Profile →npx skills add calesthio/generative-media-skills --skill podcast-production --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Designs and produces a spoken-word podcast episode or show bible using generative tools, including format selection, scripting for the ear, voice casting and TTS direction, episode structure, rights handling, loudness and delivery standards, metadata, transcripts, and AI-disclosure QA before publishing. It is intended for episodes or show bibles, and for decisions on production, rights, disclosure, or delivery for spoken-word audio.
How it works
- Start with format design to determine show type (e.g., two-host, interview, solo, narrative, news brief) and show bible details (premise, cadence, voice identity, signature elements, disclosure stance).
- Write scripts tailored for the ear, prioritizing short sentences, contractions, front-loaded conclusions, signposted transitions, and readable numbers/URLs. For formats with high risk moments, script fully; for conversational formats, outline the middle.
- Cast multiple voices with attention to distinctness and consistency; lock each persona’s voice configuration and generate dialogue in speaker-specific configurations; apply pronunciation controls via phoneme markup, lexicon, or spelling as needed; normalize numbers and dates.
- Direct performance, pacing, and emotion using punctuation, SSML controls where supported, and multiple takes to select the best delivery; engineer chemistry for on-script dialogue.
- Structure episodes with cold open, intro/theme, teaser, body/segments, ad slots, and outro; for narratives, apply act structure inside the body.
- Assemble and edit: level dialogue first, then add music/SFX, duck beds under speech, trim artifacts, maintain consistent room tone, and match levels across segments; plan for final loudness pass.
- Manage ad slots as baked-in or dynamic; ensure disclosures apply to ads if using synthetic voices.
- Decide between fully-synthetic vs hybrid production; ensure consent and rights for voice cloning and any human recordings; comply with platform AI-disclosure policies.
- QA and metadata: verify RSS metadata, transcripts, and policy disclosures before publishing.
When to use it
Use when the deliverable is a podcast episode or show bible, or when an agent must make production, rights, disclosure, or delivery decisions for spoken-word audio.
What it can touch
The skill references and coordinates with multi-voice TTS and voice-identity controls, pronunciation handling, show bible contents, and metadata/QA steps, but does not itself execute music production, single-line prompts, or non-audio video tasks.
Caveats
- Emphasizes the need for explicit, written consent for voice cloning and adherence to platform AI-disclosure policies and legal considerations; cites statutory examples and evolving law as of 2026-07-10.
- Specifies that the approach is provider-neutral and focuses on craft (format, scripting, voice direction, rights, loudness, and QA) regardless of tool choice."
# Podcast production with generative tools This skill covers producing a finished, publishable podcast episode when some or all of the audio is machine-generated. It is provider-neutral: it names TTS engines, music libraries, and hosts only as illustrative options, never as the method. The craft — format design, writing for the ear, voice direction, structure, rights, loudness, delivery, disclosur
What does the podcast-production skill do?
Produce audio-first podcast episodes with generative tools — design the show and episode format (interview, narrative, news brief, two-host conversational), write scripts for the ear, decide between fully-synthetic and hybrid (recorded human + synthetic) production and meet the disclosure duty each triggers, cast and direct multi-voice TTS for consistency and chemistry, build episode structure (cold open, intro/outro, segments, ad slots), assemble and edit, clear music and SFX rights, hit podcast loudness and delivery standards, ship metadata/chapters/transcripts through RSS, and pass platf
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill podcast-production --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.