Azure Realtime Podcast Generation

What it does

When your agent uses it

• Adding text-to-speech narration to a web app with the Azure OpenAI Realtime API
• Generating a podcast-style audio summary from written content
• Converting raw PCM audio from the Realtime API into WAV

Example prompts

• “Add an endpoint that turns an article into a podcast-style narration using GPT Realtime Mini.”
• “Write the React component that plays back the base64 WAV from our backend.”
• “Convert the PCM chunks we collect from the Realtime API into a WAV file.”

Requirements

• An Azure OpenAI resource with a GPT Realtime Mini deployment
• Python with FastAPI

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Configure environment variables for Realtime API
2. 2Connect via WebSocket to Azure OpenAI Realtime endpoint
3. 3Send text prompt, collect PCM audio chunks + transcript
4. 4Convert PCM to WAV format
5. 5Return base64-encoded audio to frontend for playback

What it can do on your machine

Read from SKILL.md and the folder at commit 354361d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • AZURE_OPENAI_AUDIO_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Azure Realtime Podcast Generation loads about 947 tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 150 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~101

When it runs · the whole SKILL.md, loaded when a task matches

~947

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from microsoft/skills at commit 354361d, republished under its MIT licence (© microsoft). 150 words, ~947 tokens.

name

podcast-generation

description

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.

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

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)

// 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();

© microsoft, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in .github/skills/podcast-generation of microsoft/skills.

• SKILL.md
• references/architecture.md
• references/code-examples.md
• scripts/pcm_to_wav.py

Open the folder on GitHubat commit 354361d

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in microsoft/skills, which our catalogue first saw on October 7, 2026.

• aiskillstore/marketplaceskills/sickn33/podcast-generation