podcast

Convert text into podcast-style audio using the browser's Web Speech API.

13|2|Updated Nov 23, 2025

Search Tags:#automation #dialogue #audio #podcast #browser #multilingual #tts

Ready to run

npx skills add https://github.com/sgasser/claude-skill-podcast --skill podcast

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: podcast
Source: https://github.com/sgasser/claude-skill-podcast/tree/main/podcast
Command: npx skills add https://github.com/sgasser/claude-skill-podcast --skill podcast

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

This Skill lets you generate podcast-style audio from text directly in the browser using the built-in Web Speech API. No external APIs or keys are required, so you can produce multi-language podcasts quickly and at zero cost.

Core Features & Use Cases

Browser-based TTS: Create audio podcasts without sending data to third-party services.
Multi-Language & Voices: Detect language and select platform-appropriate voices for iOS, Android, and desktop.
Host-Expert Dialogue: Automatically formats text into a natural host and expert conversation.
TTS-Friendly Formatting: Applies writing rules to improve pronunciation and flow.
Interactive Player: Play, pause, resume, and jump to specific lines within the transcript.
From Any Content: Convert articles, lists, topics, or your own dialogue into a podcast episode.

Quick Start

Ask Claude to create a podcast from a text source or topic. For example:

"Create a podcast about the history of artificial intelligence."
"Convert this article into a host-expert podcast dialogue."

Frequently Asked Questions about podcast

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

FAQPage Schema

How do I convert text into podcast audio in the browser?▼

Text-to-podcast conversion uses the browser's built-in Web Speech API to generate audio directly without external services. Provide your text, dialogue, or article—the Skill formats it as host-expert conversation, applies TTS-friendly rules, detects language, and renders audio with platform-appropriate voices for iOS, Android, and desktop.

Can I create multilingual podcasts without API keys?▼

Yes. Browser-based text-to-speech operates entirely offline with automatic language detection and no API keys required. The Skill selects voices appropriate to each detected language and platform, letting you produce multilingual podcasts at zero cost.

What types of content can I turn into podcast dialogue?▼

Any text source—articles, lists, topics, or pre-written dialogue—can become podcast audio. The Skill automatically structures content into natural host-expert conversation, applies formatting rules to improve pronunciation, and outputs an interactive player with play, pause, resume, and transcript navigation.

Does browser-based text-to-speech work on all devices?▼

The Skill uses the Web Speech API, which is supported across modern browsers on iOS, Android, and desktop. Platform-aware voice selection adapts available voices to each device, though voice availability depends on the operating system's built-in TTS capabilities.

What's the difference between this and sending audio to external TTS services?▼

Browser-based generation keeps your data local, requires no API keys or accounts, and incurs zero cost. External services offer more voice options and quality tuning but introduce latency, dependency on third-party uptime, and privacy considerations around data transmission.

How does the Skill handle dialogue formatting for natural podcast flow?▼

The Skill applies TTS-friendly writing rules to improve pronunciation and readability, structures content into host-expert turns, and formats output as a JSX file with platform-aware voice selection and transcript metadata for interactive playback control.