fal-audio-podcast

Generate multi-speaker podcast audio from dialogue scripts using Fal.ai VibeVoice 7B.

199|25|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/refly-ai/refly-skills --skill fal-audio-podcast
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fal-audio-podcast
Source: https://github.com/refly-ai/refly-skills/tree/main/skills/fal-audio-podcast
Command: npx skills add https://github.com/refly-ai/refly-skills --skill fal-audio-podcast

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 podcast audio with multiple speakers from dialogue scripts, eliminating the need for manual voice recording and editing.

Core Features & Use Cases

  • Multi-Speaker Audio Generation: Create podcast-style conversations with up to 4 distinct AI voices.
  • Script-to-Audio Conversion: Transform written dialogue into natural-sounding audio content.
  • Use Case: A content creator needs to produce a short podcast episode discussing a new product. They can provide the script with speaker assignments, and the Skill will generate the audio with distinct voices for each speaker.

Quick Start

Use the fal-audio-podcast skill to generate a podcast from the provided script.

Frequently Asked Questions about fal-audio-podcast

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

FAQPage Schema
How do I generate multi-speaker podcast audio from a script?

To generate multi-speaker podcast audio, you provide a dialogue script with speaker assignments to the Skill, which uses the Fal.ai VibeVoice 7B model to convert the text into natural-sounding audio. It supports up to four distinct AI voices.

Can I create a podcast with more than two AI voices?

Yes, you can create a podcast with up to four distinct AI voices. The Skill supports multi-speaker audio generation, allowing you to assign different voices to different speakers in your dialogue script for natural-sounding conversations.

Does Fal.ai VibeVoice work for converting written dialogue into audio?

Yes, Fal.ai VibeVoice 7B converts written dialogue into podcast-style audio. It transforms text scripts with speaker assignments into natural-sounding multi-voice audio content, eliminating the need for manual voice recording and editing.

What is the maximum number of speakers supported for AI podcast generation?

The maximum number of speakers supported for AI podcast generation is four. The Skill uses the VibeVoice model to produce professional multi-voice audio content from dialogue scripts with up to four distinct AI voices.

Do I need manual voice recording to produce multi-voice podcast content?

No, you do not need manual voice recording or editing to produce multi-voice podcast content. The Skill automates the creation of professional-sounding podcast audio by converting dialogue scripts directly into natural-sounding audio with distinct AI voices.