podcast-generation

Generate two-host conversational podcasts from text into MP3 audio.

79.6k|10.9k|Updated May 7, 2025
One-click install
npx skills add https://github.com/bytedance/deer-flow --skill podcast-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generation
Source: https://github.com/bytedance/deer-flow/tree/main/skills/public/podcast-generation
Command: npx skills add https://github.com/bytedance/deer-flow --skill podcast-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation of professional-sounding podcasts from written content, transforming articles or documents into natural, conversational audio.

Core Features & Use Cases

  • Text-to-Podcast Conversion: Converts any text into a two-host (male/female) conversational podcast.
  • Multi-language Support: Handles both English and Chinese content.
  • Automated Audio Generation: Synthesizes speech and mixes audio into an MP3 file.
  • Use Case: Generate a podcast summary of a long technical document or a news article for easy listening on the go.

Quick Start

Use the podcast-generation skill to create a podcast from the provided article text.

Frequently Asked Questions about podcast-generation

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

FAQPage Schema
How do I convert text into a conversational podcast?▼

To convert text into a conversational podcast, provide your written article or document to the Skill. It transforms the material into a two-host dialogue, synthesizes speech, and mixes the audio into an MP3 file.

Can I generate text-to-speech audio in both English and Chinese?▼

Yes, the text-to-speech audio generation supports both English and Chinese content. It converts written material into a two-host conversational format and synthesizes the dialogue in your chosen language.

Do I need a Volcengine TTS API key to generate audio?▼

Yes, you need Volcengine TTS API credentials to generate audio. The Skill requires these credentials to synthesize speech from text and mix the conversational podcast into a final MP3 file.

What is the best way to turn a long technical document into a podcast?▼

The best way to turn a long technical document into a podcast is using automated text-to-podcast conversion. It transforms written content into a natural two-host conversational audio format for easy listening.

Does podcast generation support single-host audio formats?▼

No, the podcast generation Skill focuses on a two-host male and female conversational format. It converts written text into natural dialogue rather than supporting single-host audio formats.

How does automated podcast generation handle text content?▼

Automated podcast generation handles text content by converting written articles into a two-host conversational dialogue. It then synthesizes speech and mixes the conversational audio into an MP3 file.