realtime-audio-narration

Turns written content into spoken, podcast-style audio through the Azure OpenAI Realtime API over WebSockets, covering credentials setup, streamed PCM capture, WAV packaging, a FastAPI serving endpoint, and browser playback. Use when the user wants to narrate articles, notes, or scripts as audio, build a streaming text-to-speech backend, add selectable narration voices to an app, or fix silent output, rejected requests, or distorted playback from the Realtime API. Not for music or song generation, transcribing existing recordings into text, or building live two-way voice agents.

Version

v1.0.0

Size

14 KB

Updated

2026-10-06

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.