AI Podcast Creation — workflow skill for voice & voiceover

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Produce audio podcasts and audiobooks with multi-voice TTS, music beds, intros, outros and ffmpeg.

• Type: Workflow · Voice & voiceover
• Slug: inference-sh-ai-podcast-creation
• Status: live
• Publisher: inference.sh (vendor, verified)
• License: MIT
• Source: https://github.com/inference-sh/skills/tree/main/guides/content/ai-podcast-creation
• Works in: Claude Code, Codex, Cursor, Gemini CLI
• Requires: inference.sh account, belt CLI (belt login), FFmpeg
• Cost: Billed by inference.sh
• Adoption: 6 installs, 781 GitHub stars (skills.sh, 2026-10-26)

What it does

Creates audio podcasts with text-to-speech, music and editing on inference.sh: multi-voice conversations with Kokoro, Dia TTS or Chatterbox, AI background music, intros and outros. Full episodes are assembled with ffmpeg.

Use when

• An audio-only podcast episode
• An audiobook or narrated article

Install

• Claude Code: npx skills add inference-sh/skills --skill ai-podcast-creation -a claude-code
• Codex: npx skills add inference-sh/skills --skill ai-podcast-creation -a codex
• Cursor: npx skills add inference-sh/skills --skill ai-podcast-creation -a cursor
• Gemini CLI: npx skills add inference-sh/skills --skill ai-podcast-creation -a gemini-cli

Models it drives: kokoro, dia-tts, chatterbox

More voice & voiceover skills

• ElevenLabs Dubbing: Dub video and audio into other languages while keeping each original speaker's voice.
• ElevenLabs Text to Speech: Turn scripts into natural voiceover in 90+ languages with ElevenLabs voices, streaming and stitching.
• ElevenLabs Voice Changer: Re-voice a recording in a different voice while keeping its emotion, timing and delivery.
• AI Voice Cloning: Generate expressive voices in 100+ languages with Inworld TTS-2, ElevenLabs and more, from one CLI.
• Dialogue Audio: Produce multi-speaker dialogue audio with speaker tags, emotion and pacing for podcasts and explainers.
• ElevenLabs Dialogue: Generate a whole multi-voice conversation as one audio file with ElevenLabs, from a script.