Podcast Generation (Microsoft)
3,066 starsMicrosoft's official skill for generating AI podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model over WebSocket — full-stack implementation from content to real audio output.
- First published：2026-01-16
- data as of：
- 2026-09-30
- Licence：
- MIT
When to use it
When turning articles or content into podcast-style dialogue audio, or building TTS narrative features.
Caution
Requires Azure OpenAI (paid) with Realtime API access; the Microsoft repo defaults to the GitHub Copilot directory (.github/skills) for installation.
Install prompt
請幫我安裝「Podcast Generation (Microsoft)」技能：從 https://github.com/microsoft/skills/tree/main/.github/skills/podcast-generation（技能路徑：.github/skills/podcast-generation/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.
Compatible with
Related patterns