AI Podcast Voiceover Skill

👉 See also AI Audiobook Generator Skill

Turn an article, notes, or a finished script into a solo podcast episode with a consistent host voice, natural pacing, pronunciation control, and an MP3 you can publish, from inside Claude Code, Cursor, Codex, Windsurf, Cline, or OpenClaw.

Important

Rendering needs a Beatra account and uses credits. The skill itself is free to install.

Question	Answer
What it does	Turn an article, notes, or finished script into a listenable solo podcast episode with a consistent host voice, natural pacing, pronunciation control, and MP3 delivery.
Models	MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo, Suno 6, MiniMax Music 3.0
Requirements	Python 3.10+ and an agent that loads `SKILL.md`
Cost	Free to install. Each render uses credits on your Beatra account, and paid steps run only when you ask for that exact render or approve its card.
Works with	Claude Code, Cursor, Codex, Windsurf, Cline, OpenClaw

Cover art for The Small Studio Show, a fictional solo podcast about shipping side projects. AI-generated with Beatra.

Skill	Entry point	Version
`ai-podcast-voiceover`	SKILL.md	0.2.8

This repository is published automatically from beatra-ai/beatra-skills. Report issues there.

Install

With the skills CLI:

npx skills add beatra-ai/ai-podcast-voiceover-skill

As a Claude Code plugin:

claude plugin marketplace add beatra-ai/ai-podcast-voiceover-skill
claude plugin install ai-podcast-voiceover@ai-podcast-voiceover-skill

As a Codex plugin:

codex plugin marketplace add beatra-ai/ai-podcast-voiceover-skill
codex plugin add ai-podcast-voiceover@ai-podcast-voiceover-skill

As a GitHub Copilot CLI plugin:

copilot plugin marketplace add beatra-ai/ai-podcast-voiceover-skill
copilot plugin install ai-podcast-voiceover@ai-podcast-voiceover-skill

As a Gemini CLI extension:

gemini extensions install https://github.com/beatra-ai/ai-podcast-voiceover-skill

With the GitHub CLI:

gh skill install beatra-ai/ai-podcast-voiceover-skill ai-podcast-voiceover

Or clone this repository and copy skills/ai-podcast-voiceover into ~/.claude/skills/ for Claude Code, ~/.cursor/skills/ for Cursor, ~/.agents/skills/ for Codex, ~/.codeium/windsurf/skills/ for Windsurf, ~/.cline/skills/ for Cline, or ~/.openclaw/skills/ for OpenClaw.

Or paste this into your agent:

Install the ai-podcast-voiceover skill from https://github.com/beatra-ai/ai-podcast-voiceover-skill (folder skills/ai-podcast-voiceover), then follow its SKILL.md to connect my Beatra account.

Examples

▶ Listen (MP3)

Episode 12 of The Small Studio Show, a 50-second solo episode read by one host voice from a short script about giving side projects a Friday deadline. AI-generated with Beatra.

Ask your agent:

Turn ./episode-12-script.md into episode 12 of The Small Studio Show: one consistent host voice, conversational pacing, and give me an MP3 I can publish.

Prompt:

Welcome to The Small Studio Show. This is Episode twelve: why your side project needs a Friday deadline.

Most side projects don't die from bad ideas. They die from "someday."

So here's my point. Pick one small, shippable piece, and give it a deadline: this Friday, five p.m. Not a launch. Just one thing a real person can see. A landing page. A demo video. A working sign-up form.

Why Friday? A week is short enough to feel urgent, and long enough to finish something real. When Friday comes, ship what you have, even if it's rough.

Your takeaway: next Monday, write down one Friday deliverable, and tell one friend.

That's it for today. Keep it small, keep it shipping. See you next week.

Technical Specifications & Output Limits

As of 2026-10-18. Live list: https://docs.beatra.ai/en/docs/models

Uploads — up to 100 MB per file; the per-model input limits below also apply
Text to speech — 2 models (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo); FLAC, MP3, OPUS, PCM, WAV; 40 languages; sample rates 8, 16, 22.05, 24, 32, 44.1 kHz; up to 50000 characters per request
- Languages (ISO 639 codes): zh, yue, en, es, fr, ru, de, pt, ar, it, ja, ko, id, vi, tr, nl, uk, th, pl, ro, el, cs, fi, hi, bg, da, he, ms, fa, sk, sv, hr, fil, hu, no, sl, ca, nn, ta, af
Text to music — 2 models (Suno 6, MiniMax Music 3.0); MP3
- Suno 6: prompt up to 500, lyrics up to 5000, title up to 80 characters
- MiniMax Music 3.0: prompt up to 2000, lyrics up to 3500, title up to 100 characters
Reference audio to music — 2 models (Suno 6, MiniMax Music 3.0); MP3
- Suno 6: prompt up to 500, lyrics up to 5000, title up to 80 characters; reference audio 6–480 s (FLAC, MP3, WAV)
- MiniMax Music 3.0: prompt up to 300, lyrics up to 1000, title up to 100 characters; reference audio 6–360 s, up to 50 MB (FLAC, MP3, WAV)

Why use Beatra instead of calling model APIs directly

One account for every model this skill uses — Text to speech 2; Text to music 2; Reference audio to music 2 (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo, Suno 6, MiniMax Music 3.0) (as of 2026-10-18), behind one Beatra sign-in; no keys from individual model providers to manage.
You decide what gets paid for — Paid renders run only when you ask for that exact render or approve its card, which shows the live credit estimate.
Direction before rendering — the skill plans, directs, and reviews the work, then renders it on Beatra.
Files you can verify — every file under skills/ matches the release archive on cdn.beatra.ai byte for byte, checked by SHA-256 before each push.
Updates you control — no self-updater; update with the tool you installed it with.
Runs in your agent — Claude Code, Cursor, Codex, Windsurf, Cline, OpenClaw.

What you get

Make source material easy to hear — Turn articles, notes, and finished writing into a spoken episode with clear transitions, natural rhythm, and listener-friendly structure.
Keep the host direction consistent — Choose a fitting current voice, keep names and specialist terms clear, and reuse the show direction as new episodes take shape.
Shape each episode with clarity — Bring the script, host direction, pronunciation notes, and episode focus together in one listener-ready production brief.

Use cases

Article-to-podcast audio — Turn an article, newsletter, or research note into a focused episode that listeners can follow from the opening through the close.
News and expert commentary — Give explainers, analysis, and knowledge shows a steady host voice with clear names, numbers, and technical terms.
Branded solo series — Build a familiar host direction for recurring insight, education, and founder-led podcast episodes.
Podcast trailers and show introductions — Create concise trailer, opener, and recurring sign-off audio that helps a show sound cohesive across episodes.

FAQ

What can AI Podcast Voiceover create?

It turns supplied articles, notes, outlines, and finished scripts into listener-friendly solo podcast episodes, with a selected host voice, natural pacing, clear pronunciation, and MP3 episode audio.

Can I keep one host voice across a series?

Yes. Choose a host direction for the show and reuse its voice, language, delivery settings, opener, closer, and pronunciation notes as later episodes are prepared.

What material works well for a podcast episode?

Articles, newsletters, research notes, expert commentary, show outlines, and final scripts all provide strong starting points for an episode tailored to listeners.

Updates and security

Since the 2026-10 release, this skill contains no self-updater: it runs only the files you installed and never replaces them on its own. Update it with the tool you installed it with — npx skills update ai-podcast-voiceover or gh skill update ai-podcast-voiceover. Details: references/updates-and-security.md inside the skill.

License

MIT-0 — free to use, modify, and redistribute, including commercially. No attribution required. Same terms as these skills carry on ClawHub.