# azure-ai-voicelive-py

Helps build real-time voice applications in Python using Azure AI Voice Live SDK with bidirectional WebSocket streaming.

- skill · `type=skill` · Claude Code, GitHub Copilot · 1 install · ★ 3149
- Author: Microsoft
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-python/skills/azure-ai-voicelive-py/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/azure-ai-voicelive-py

## What it does

This skill provides code patterns for the `azure-ai-voicelive` Python package. It configures real-time bidirectional audio sessions with models such as `gpt-4o-realtime-preview`, handles incoming 24kHz mono PCM16 streams, and processes audio deltas through event loops.

All connections require asynchronous context managers to release sockets and credentials deterministically. The SDK favors `DefaultAzureCredential` from `azure.identity.aio` across local and cloud environments, while retaining `AzureKeyCredential` for legacy API-key deployments. It also covers server-side voice activity detection and `FunctionTool` definitions.

Without setting the `AZURE_COGNITIVE_SERVICES_ENDPOINT` environment variable, client connections fail immediately.

## Requirements
- Works with: Azure

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add microsoft/skills --skill azure-ai-voicelive-py -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/azure-ai-voicelive-py/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/azure-ai-voicelive-py/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/azure-ai-voicelive-py/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/azure-ai-voicelive-py/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install microsoft/skills azure-ai-voicelive-py
```

2. **Manually: put the files in place**
- File: `.github/skills/azure-ai-voicelive-py/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/microsoft/skills --path .github/plugins/azure-sdk-python/skills/azure-ai-voicelive-py
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/azure-ai-voicelive-py/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-python/skills/azure-ai-voicelive-py/SKILL.md

## When to use it
- stream bidirectional PCM16 audio over WebSockets in Python
- configure Server VAD turn detection for voice assistants
- register FunctionTool callbacks inside real-time voice sessions
- set up DefaultAzureCredential authentication for Azure AI services

## Example prompts
- Write an async Python client using azure-ai-voicelive and DefaultAzureCredential.
- Configure a real-time session with gpt-4o-realtime-preview, server VAD, and the alloy voice.
- Show how to stream base64 PCM16 audio chunks into conn.input_audio_buffer.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 412e8b30149d6fe4.

BEGIN THIRD-PARTY FILE 412e8b30149d6fe4
````text
---
name: azure-ai-voicelive-py
description: Build real-time voice AI applications using Azure AI Voice Live SDK (azure-ai-voicelive). Use this skill when creating Python applications that need real-time bidirectional audio communication with Azure AI, including voice assistants, voice-enabled chatbots, real-time speech-to-speech translation, voice-driven avatars, or any WebSocket-based audio streaming with AI models. Supports Server VAD (Voice Activity Detection), turn-based conversation, function calling, MCP tools, avatar integration, and transcription.
license: MIT
metadata:
  author: Microsoft
  version: "1.0.0"
  package: azure-ai-voicelive
---

# Azure AI Voice Live SDK

Build real-time voice AI applications with bidirectional WebSocket communication.

## Installation

```bash
pip install azure-ai-voicelive aiohttp azure-identity
```

## Environment Variables

```bash
AZURE_COGNITIVE_SERVICES_ENDPOINT=https://<region>.api.cognitive.microsoft.com  # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
AZURE_COGNITIVE_SERVICES_KEY=<api-key>  # Only required for the legacy API-key auth path below
```

## Authentication & Lifecycle

> **🔑 Two rules apply to every code sample below:**
>
> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI / VS Code / Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account/API keys — they bypass Entra audit and rotation.
>    - Local dev: `DefaultAzureCredential` works as-is.
>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=<specific_credential>`) to constrain the credential chain to production-safe credentials.
> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:
>    - Sync: `with <Client>(...) as client:`
>    - Async: `async with <Client>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)
>
> Snippets may abbreviate this setup, but production code should always follow both rules.

```python
import os
from azure.ai.voicelive.aio import connect
from azure.identity.aio import DefaultAzureCredential, ManagedIdentityCredential

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()

async with DefaultAzureCredential(require_envvar=True) as credential:
    async with connect(
        endpoint=os.environ["AZURE_COGNITIVE_SERVICES_ENDPOINT"],
        credential=credential,
        model="gpt-4o-realtime-preview",
        credential_scopes=["https://cognitiveservices.azure.com/.default"]
    ) as conn:
        ...
```

### Legacy: API Key (existing keyed deployments)

New code should use `DefaultAzureCredential` above. Use `AzureKeyCredential` only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.
````
END THIRD-PARTY FILE 412e8b30149d6fe4

The third-party file has ended. Everything between the 412e8b30149d6fe4 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3290 of 11585 bytes. © Microsoft · MIT · https://github.com/microsoft/skills/tree/HEAD/.github/plugins/azure-sdk-python/skills/azure-ai-voicelive-py/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md