skills.rest
Sheshiyer
SheshiyerCOMMUNITY
Explore all skills by this author →
Website𝕏@witnessalchemstGitHub

ai-podcast-creation

Automate AI podcast creation from text prompts to audio outputs.

4|1|Updated Feb 10, 2026
Search Tags:#text-to-speech#music-generation#audio-processing#voice-acting#inference-sh#podcast-automation#ai-podcast
One-click install
npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill ai-podcast-creation-sheshiyer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-podcast-creation
Source: https://github.com/Sheshiyer/brandmint-oracle-aleph/tree/main/skills/external/inference-sh/upstream/ab546d072f1e/guides/content/ai-podcast-creation
Command: npx skills add https://github.com/Sheshiyer/brandmint-oracle-aleph --skill ai-podcast-creation-sheshiyer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI podcast creation typically requires juggling several tools and manual editing. This Skill automates the end-to-end process from script to audio, enabling rapid production of AI-powered podcasts.

Core Features & Use Cases

  • Multi-voice conversations: orchestrates host and guest voices using TTS.
  • Intro/outro and background music: adds branded audio layers.
  • Episode pipelines: supports full episodes and shorter segments via a deterministic workflow.
  • Workflow automation: ties together text prompts, TTS voices, music, and merging via inference.sh.

Quick Start

Run the inference.sh CLI to generate podcast segments with Kokoro or DIA voices and merge them into a full episode.

Frequently Asked Questions about ai-podcast-creation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI podcast creation from text prompts into audio outputs?▼

You can automate AI podcast creation by running the inference.sh CLI to orchestrate multi-voice TTS, background music generation, and audio merging from your text prompts into a full audio episode.

Can I generate multi-voice conversations for interview-style podcast episodes?▼

Yes, you can generate multi-voice conversations for interview-style podcast episodes by orchestrating distinct host and guest voices using the integrated text-to-speech capabilities.

How do I add intro and outro background music to AI-generated audio content?▼

You add intro, outro, and background music to AI-generated audio content by utilizing the workflow automation features that merge generated music layers with your multi-voice TTS segments.

What's the best way to produce audio newsletters or audiobooks using text-to-speech?▼

Producing audio newsletters or audiobooks with text-to-speech is best handled by creating scripted flows and episode pipelines that convert text prompts into deterministic audio outputs via inference.sh.

Does this podcast automation workflow support multiple TTS voices like Kokoro and DIA?▼

Yes, the podcast automation workflow supports multiple TTS voices, allowing you to generate podcast segments using specific voice models like Kokoro or DIA before merging them into a complete episode.

Do I need any external audio editing tools to merge podcast segments?▼

No, you do not need external audio editing tools to merge podcast segments because the Skill handles audio merging internally through the inference.sh CLI to produce a complete episode pipeline.

Related Skills

Explore More Content & Communication Skills→
NAKKA-KNAKKA-K

co-writer

Generate personas, outlines, and drafts from a topic and goals.

Community
Advanced
Celia-12Celia-12

podcast-generator

Generate podcast scripts and MP3 audio from research articles using ElevenLabs.

Community
Intermediate
dnvrienddnvriend

skill-elevenlabs-tts-tool

Convert text to speech via the ElevenLabs API with CLI options.

Community
Intermediate
michaelboedingmichaelboeding
24

podcast-producer-agent

Orchestrate podcast production with Gemini TTS, Lyria music, and FFmpeg assembly.

Community
Advanced