skills.rest
microsoft
microsoftOFFICIAL
Explore all skills by this author →
Website𝕏@OpenAtMicrosoftGitHub

podcast-generation

Generate podcast-style audio narratives from written content via WebSocket streaming.

2.9k|323|Updated Jan 16, 2026
Search Tags:#real-time#podcast#websocket#narration#audio-generation#azure-openai
One-click install
npx skills add https://github.com/microsoft/skills --skill podcast-generation-microsoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-generation
Source: https://github.com/microsoft/skills/tree/main/.github/skills/podcast-generation
Command: npx skills add https://github.com/microsoft/skills --skill podcast-generation-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Converts written content into engaging podcast-style audio narratives by leveraging Azure OpenAI's Realtime API and WebSocket streaming, enabling automated narration generation.

Core Features & Use Cases

  • End-to-end podcast narration: from text input to PCM audio streamed in real-time.
  • Frontend-backend integration: React frontend with FastAPI backend and WebSocket streaming for live narration.
  • Use Case: Create narrations for articles, blog posts, or transcripts to produce shareable audio content.

Quick Start

Provide content text and choose a voice style to generate a podcast-style narration.

Frequently Asked Questions about podcast-generation

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

FAQPage Schema
How do I convert a blog post into podcast-style audio narration?▼

Yes, you can stream audio narration in real-time to a frontend. The system uses a FastAPI backend with WebSocket streaming to deliver live PCM audio data, enabling immediate frontend playback integration during generation.

Does the podcast-generation workflow support React frontend integration?▼

Yes, the podcast-generation workflow supports React frontend integration. It pairs a React frontend with a FastAPI backend and WebSocket streaming to handle live narration playback and end-to-end audio delivery.

How do I convert PCM audio to WAV format after WebSocket streaming?▼

To convert PCM audio to WAV format after WebSocket streaming, the workflow applies a PCM-to-WAV conversion process. This handles the raw audio chunks received from the WebSocket connection and formats them into a playable WAV file.

Do I need Azure OpenAI's Realtime API to generate audio narratives?▼

Yes, you need Azure OpenAI's Realtime API to generate audio narratives. The workflow uses the Realtime Mini model via a WebSocket connection to process text input and stream the resulting podcast-style audio narration.

What is the best way to generate audio from article transcripts automatically?▼

The best way to generate audio from article transcripts automatically is using an automated narration workflow. It ingests transcript text, applies optional voice style control, and streams the resulting audio content directly through a WebSocket connection.

Related Skills

Explore More Content & Communication Skills→
sgassersgasser
13

podcast

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

Community
Basic
RemseyMailjardRemseyMailjard

podcast-generation

Convert text content into streaming podcast-style audio via WebSocket.

Community
Advanced
IvanMurzakIvanMurzak
3.8k

unity-version-split

Split C# files into Unity 6.5+ and pre-6.5 variants with preprocessor guards.

Community
Intermediate
RealEmmettSRealEmmettS

openai-audio

Integrate OpenAI audio APIs for voice agents and real-time transcription.

Community
Advanced