Skip to main content
skill CX Codex

ai-podcast — Claude Code skill: what it does, how to install

ai-podcast builds multi-character talking head video podcasts from scratch using inference.sh tools for portrait rendering, speech synthesis, and clip stitching.

no license 238 installs ★ 31 updated 2026-08-31

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add 101-skills/superpowers --skill ai-podcast -a claude-code
Open on GitHub

What ai-podcast does

This skill guides the agent through an automated multi-speaker video workflow. It starts by setting up character portraits via pruna/p-image, Phota, or Gemini image models. Once dialog lines and pacing are settled, speech tracks are rendered with inworld/text-to-speech-2 at a default conversational tempo of 1.05.

Individual speaking turns are animated into video clips using pruna/p-video-avatar. Each clip must run sequentially because concurrent rendering runs out of GPU memory and triggers CUDA OOM errors. Finally, infsh/media-merger stitches the clips into an MP4 file at 24 frames per second.

You need the infsh CLI and access to the corresponding model endpoints. Preserving consistent human faces across camera angles also requires training a Phota profile beforehand with 30 to 50 reference portraits.

What it helps with

  • Produce multi-character talking head podcasts without video equipment
  • Synthesize realistic conversational speech turn by turn
  • Animate still character portraits to match generated voice tracks
  • Stitch alternating speaker angles into a finished MP4 file

Example prompts for the agent

  • Create a 30-second AI podcast debating product pricing with two speakers
  • Render character portraits and voice tracks for an illustrated mascot dialogue
  • Animate speaker turns and stitch the final video using the inference pipeline

How to install ai-podcast

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-podcast -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-podcast/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-podcast/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ai-podcast

How to install ai-podcast in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-podcast -a claude-code in your terminal.

What does ai-podcast do?

It orchestrates character image generation, voice synthesis, avatar animation, and video assembly into a unified multi-speaker video podcast.

Why does avatar video generation need to run sequentially?

Running multiple pruna/p-video-avatar jobs concurrently exhausts GPU VRAM, causing CUDA out-of-memory failures.

Similar skills

All skills for AI and ML →

From the same set81

The whole set →
javascript-sdk javascript-sdk teaches the agent to wire the inference.sh JavaScript/TypeScript client into your app: running AI apps, streaming progress and building agents in code. CX Codex +1 239installs llm-models llm-models queries over a hundred LLMs through OpenRouter using the belt command-line tool directly from your agent. Selects cost-effective models automatically. CX Codex +1 238installs press-release-writing press-release-writing is a Claude Code skill that writes AP-style press releases with an inverted pyramid, triggered by product launches, funding rounds, partnerships, and company news. CX Codex +1 238installs customer-persona customer-persona turns market search into a buyer persona: demographics, psychographics, goals, quantified pain points and a generated portrait. For strategy decks and product decisions. CX Codex +1 238installs ai-podcast-creation ai-podcast-creation is a Claude Code skill that turns text into spoken podcasts with multiple voices, generated music, and merged audio. It also supports audiobook narration and document-based discussions. CX Codex +1 238installs elevenlabs-music elevenlabs-music creates original music from text prompts through ElevenLabs and inference.sh. Use it for background tracks, jingles, podcasts, videos, or games. CX Codex +1 238installs elevenlabs-voice-changer elevenlabs-voice-changer swaps the speaker in a recording for one of the ElevenLabs voices while the words and delivery stay. Handy for dubbing, characters, anonymising. CX Codex +1 238installs flux-image flux-image is a Claude Code skill that runs FLUX models through the belt CLI for text-to-image generation, image transformation, and custom LoRA styles. CX Codex +1 238installs

Project sponsors

Companies that keep this analytics open