podcast-generation

Synced v1.1.0 License: MIT Source: microsoft/skills/.github/skills/podcast-generation Commit: cde32f9 Latest included change: 2026-01-28

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

Summary

Purpose: Explains how to turn text into spoken narratives with Azure OpenAI Realtime and prepare the audio for playback.
When to use: Use it when a service needs to stream narration from text over a WebSocket and deliver playable audio to a web frontend.
Outputs: It collects 24 kHz, 16-bit mono PCM audio and transcript text, then converts the audio to WAV for Base64-encoded browser playback.

Upstream changes (2, latest included 2026-01-28)

a2003b6 2026-01-28 docs(skills): standardize all skills to skill-creator guidelines Removed the opening and closing ```skill fences from the podcast-generation SKILL.md file.

14224cc 2026-01-16 feat: Add skill creator scripts and templates for initializing and packaging skills Added a podcast-generation skill covering Azure OpenAI GPT Realtime Mini WebSocket audio generation, PCM-to-WAV conversion, browser playback, voice options, and API events.

npx skills add "lettucebo/Skills#v2.2.0@podcast-generation" --full-depth

⚠ Available after v2.2.0 is published

Podcast Generation with GPT Realtime Mini

Generate real audio narratives from text content using Azure OpenAI's Realtime API.

Quick Start

Configure environment variables for Realtime API
Connect via WebSocket to Azure OpenAI Realtime endpoint
Send text prompt, collect PCM audio chunks + transcript
Convert PCM to WAV format
Return base64-encoded audio to frontend for playback

Environment Configuration

AZURE_OPENAI_AUDIO_API_KEY=your_realtime_api_key
AZURE_OPENAI_AUDIO_ENDPOINT=https://your-resource.cognitiveservices.azure.com
AZURE_OPENAI_AUDIO_DEPLOYMENT=gpt-realtime-mini

Note: Endpoint should NOT include /openai/v1/ - just the base URL.

Core Workflow

Backend Audio Generation

from openai import AsyncOpenAI
import base64

# Convert HTTPS endpoint to WebSocket URL
ws_url = endpoint.replace("https://", "wss://") + "/openai/v1"

client = AsyncOpenAI(
    websocket_base_url=ws_url,
    api_key=api_key
)

audio_chunks = []
transcript_parts = []

async with client.realtime.connect(model="gpt-realtime-mini") as conn:
    # Configure for audio-only output
    await conn.session.update(session={
        "output_modalities": ["audio"],
        "instructions": "You are a narrator. Speak naturally."
    })
    
    # Send text to narrate
    await conn.conversation.item.create(item={
        "type": "message",
        "role": "user",
        "content": [{"type": "input_text", "text": prompt}]
    })
    
    await conn.response.create()
    
    # Collect streaming events
    async for event in conn:
        if event.type == "response.output_audio.delta":
            audio_chunks.append(base64.b64decode(event.delta))
        elif event.type == "response.output_audio_transcript.delta":
            transcript_parts.append(event.delta)
        elif event.type == "response.done":
            break

# Convert PCM to WAV (see scripts/pcm_to_wav.py)
pcm_audio = b''.join(audio_chunks)
wav_audio = pcm_to_wav(pcm_audio, sample_rate=24000)

Frontend Audio Playback

// Convert base64 WAV to playable blob
const base64ToBlob = (base64, mimeType) => {
  const bytes = atob(base64);
  const arr = new Uint8Array(bytes.length);
  for (let i = 0; i < bytes.length; i++) arr[i] = bytes.charCodeAt(i);
  return new Blob([arr], { type: mimeType });
};

const audioBlob = base64ToBlob(response.audio_data, 'audio/wav');
const audioUrl = URL.createObjectURL(audioBlob);
new Audio(audioUrl).play();

Voice Options

Voice	Character
alloy	Neutral
echo	Warm
fable	Expressive
onyx	Deep
nova	Friendly
shimmer	Clear

Realtime API Events

response.output_audio.delta - Base64 audio chunk
response.output_audio_transcript.delta - Transcript text
response.done - Generation complete
error - Handle with event.error.message

Audio Format

Input: Text prompt
Output: PCM audio (24kHz, 16-bit, mono)
Storage: Base64-encoded WAV

References

Full architecture: See references/architecture.md for complete stack design
Code examples: See references/code-examples.md for production patterns
PCM conversion: Use scripts/pcm_to_wav.py for audio format conversion