Skill Detail
Generate podcast-style audio narratives with Podcast Generation
Build a repeatable text-to-audio workflow around Azure OpenAI Realtime streaming, PCM collection, WAV conversion, and frontend playback for podcast-style output.
Media & TranscriptionMulti-Framework
Media & Transcription
Multi-Framework
Security Reviewed
Tool match: skills
MIT license
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill generate-podcast-style-audio-narratives-with-podcast-generation
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Azure OpenAI Realtime API access, WebSocket-capable backend, PCM to WAV conversion, frontend audio playback layer
Install & setup
Install the Microsoft skills repository with npx skills add microsoft/skills, then enable podcast-generation and configure Azure OpenAI Realtime credentials before wiring the backend streaming and frontend playback flow.
Author
Microsoft
Publisher
Organization
Last updated
Apr 21, 2026
Quick brief
Use Podcast Generation when an agent needs to implement or adapt a bounded text-to-audio pipeline for podcast-style narration using Azure OpenAI Realtime, including WebSocket setup, streaming PCM audio capture, transcript handling, WAV conversion, and playback wiring. Invoke this instead of using the product normally when the job is building the end-to-end generation workflow for narrated audio output, not general Azure OpenAI usage or a plain API listing. The boundary is podcast-style audio generation pipeline design and integration, not generic speech or media tooling.