skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-podcast-creation

Generate multi-voice podcast episodes with TTS, music, and audio merging via inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#text-to-speech#podcast#audio generation#voice synthesis#audiobook#kokoro tts#media merger
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-podcast-creation-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-podcast-creation
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/ai-podcast-creation
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-podcast-creation-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Producing podcast episodes, audiobooks, or voice content normally requires recording equipment, voice talent, and audio editing software. This Skill automates the entire pipeline by generating speech from text, creating background music, and merging segments into finished audio. ## Core Features & Use Cases - Multi-Voice TTS Generation: Create speech with Kokoro TTS, DIA TTS, or Chatterbox voices for hosts, guests, and narrators. - Full Episode Pipelines: Combine AI-generated scripts, intro/outro music, and voice segments into complete episodes using the media merger with crossfades. - NotebookLM-Style Content: Convert documents into conversational two-host podcast discussions. - Use Case: Turn a written article into a 5-minute podcast episode by generating a dialogue script with Claude, synthesizing two voices, adding intro music, and merging everything into one audio file. ## Quick Start Use the ai-podcast-creation skill to generate a podcast segment from my script with the am_michael voice and merge it with intro music.

Frequently Asked Questions about ai-podcast-creation

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

FAQPage Schema
How do I create a multi-voice AI podcast from a script?▼

Generate each speaker's lines separately with Kokoro TTS using different voice IDs like am_michael and af_sarah, then merge the resulting audio URLs with the media-merger app using a crossfade_ms parameter for smooth transitions.

What TTS voices are available for podcast generation?▼

Kokoro TTS offers voices like af_sarah, am_michael, and bf_emma for narration and hosting. DIA TTS provides natural conversational dialogue, while Chatterbox delivers expressive speech for casual content.

Can I add background music to AI-generated podcast audio?▼

Yes, generate ambient music with the ai-music app, then pass it as background_audio to the media-merger with background_volume around 0.15 so it stays subtle under the speech.

Does this skill work without the inference.sh CLI installed?▼

No, all generation commands run through the belt CLI from inference.sh. You must install it and authenticate with belt login before running any TTS, music, or merging commands.

How do I turn a document into a podcast discussion?▼

Send the document to Claude via the openrouter app with a prompt asking for a two-host conversational script, then synthesize each host's lines with different Kokoro voices and interleave them in the media merger.

Related Skills

Explore More Content & Communication Skills→
syusamasyusama
4

podcast-generation

Convert text content into a structured podcast script and synthesize dialogue into an MP3 audio file.

Community
Intermediate
zarazhangruizarazhangrui
411

podcast

Generate two-host podcast dialogue scripts and audio via Fish Audio TTS.

Community
Advanced
claude-office-skillsclaude-office-skills
368

Podcast Automation

Automate podcast production, editing, publishing, and distribution workflows.

Official
Advanced
different-aidifferent-ai
63

eleven-labs-podcast

Generate podcast audio from text files using the ElevenLabs API.

Official
Intermediate