What models does this skill support?

This skill is specifically designed for the Azure OpenAI GPT Realtime Mini model, utilizing its low-latency WebSocket capabilities.

Which programming languages are required?

The skill provides a full-stack implementation featuring a React (JavaScript/TypeScript) frontend and a Python (FastAPI) backend.

How is the audio output formatted?

The skill captures 24kHz, 16-bit, mono PCM audio chunks and includes logic to convert them into base64-encoded WAV files for browser playback.

Are different voice options available?

Yes, the skill supports various voice profiles including Alloy (Neutral), Echo (Warm), Fable (Expressive), Onyx (Deep), Nova (Friendly), and Shimmer (Clear).

Does it support real-time transcription?

Yes, the workflow handles 'response.output_audio_transcript.delta' events to provide a text transcript synchronized with the audio generation.

Podcast Narrative Generation

Name: Podcast Narrative Generation
Author: microsoft

bymicrosoft

•

1,777

•

数据科学与机器学习

Generates AI-powered audio narratives and podcasts using Azure OpenAI's Realtime API with full-stack implementation patterns.

This skill provides a comprehensive blueprint for building text-to-speech and audio narrative applications using Azure OpenAI’s GPT Realtime Mini model. It covers the end-to-end workflow from React frontend playback to Python FastAPI backend logic, including WebSocket management, PCM-to-WAV conversion, and voice customization. It is an essential resource for developers looking to integrate natural-sounding narration or real-time voice interactions into their applications using production-grade streaming patterns.

主要功能

01Support for multiple expressive voice profiles and characters

02Real-time audio streaming via WebSocket protocols

03Synchronized handling of audio deltas and text transcripts

04End-to-end implementation for React and FastAPI stacks

05Automated PCM to WAV format conversion scripts

061,777 GitHub stars

使用场景

01Converting long-form blog posts or articles into audio podcasts

02Building real-time AI narrators for interactive educational content

03Creating accessibility-focused text-to-speech features for web apps

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microsoft/skills podcast-generation

For use in Claude.ai and ChatGPT

Download Skill