skills.rest
davidrrowley
davidrrowleyCOMMUNITY
Explore all skills by this author →
Website𝕏@davidrrowleyGitHub

azure-ai-voicelive-py

Stream base64 PCM16 audio over WebSocket to Azure Voice Live.

Updated Apr 12, 2026
Search Tags:#python#azure#voice#transcription#realtime#websocket#vad
One-click install
npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-voicelive-py-davidrrowley
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: azure-ai-voicelive-py
Source: https://github.com/davidrrowley/CortexYouV3/tree/main/.agents/skills/azure-ai-voicelive-py
Command: npx skills add https://github.com/davidrrowley/CortexYouV3 --skill azure-ai-voicelive-py-davidrrowley

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Enable developers to build low-latency, bidirectional voice AI applications without managing raw WebSocket protocols or event plumbing, reducing integration complexity for real-time assistants, voice chatbots, and transcription pipelines.

Core Features & Use Cases

  • Bidirectional WebSocket Streaming: Stream base64 PCM16 audio to Azure, receive audio deltas and transcripts in real time for responsive voice assistants.
  • Turn Detection & Interrupts: Supports server VAD, Azure semantic VAD, and manual turn control for push-to-talk and interruption handling.
  • Tooling & Integration: Function calling, MCP tools, avatar/webrtc integration, transcription-only flows, and robust typed event handling for production workflows.
  • Use Case: Build a Python voice assistant that transcribes user speech, triggers a backend function for events like "get_weather", and returns synthesized audio with low latency.

Quick Start

Connect to Azure Voice Live using DefaultAzureCredential or an API key, stream microphone audio as base64 PCM16, commit the input buffer, and create a response to receive the assistant's real-time audio and transcript.

Frequently Asked Questions about azure-ai-voicelive-py

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a real-time voice assistant in Python using Azure WebSocket?▼

Build real-time voice assistants by streaming base64 PCM16 audio over Azure WebSocket connections, receiving audio deltas and transcripts with low latency. The Skill handles WebSocket protocols, authentication, and typed event handling.

How does voice activity detection work with Python real-time transcription?▼

Voice activity detection supports server VAD, Azure semantic VAD, and manual turn control for real-time transcription. These modes enable push-to-talk and interruption handling within bidirectional Python audio streaming workflows.

Can I use Azure DefaultAzureCredential for Python WebSocket audio streaming?▼

Yes, Python WebSocket audio streaming supports Azure authentication via DefaultAzureCredential or API keys. This allows secure base64 PCM16 audio streaming with append and commit semantics for real-time voice applications.

Does Python real-time voice AI support function calling and MCP tools?▼

Yes, real-time voice AI supports function calling and MCP tools alongside avatar and WebRTC integration. Backend functions trigger during transcription, returning synthesized audio with typed event handling for response lifecycle management.

What's the best way to handle turn detection and interruptions in Python voice chatbots?▼

Handle turn detection and interruptions using server VAD, Azure semantic VAD, or manual control for push-to-talk. This supports responsive voice chatbots with bidirectional WebSocket audio streaming and buffer commit semantics.

Why use base64 PCM16 audio format for Python WebSocket voice streaming?▼

Base64 PCM16 audio format enables low-latency bidirectional streaming over WebSocket connections. It supports append and commit buffer semantics, allowing real-time speech-to-speech translation and transcription services in Python.

Related Skills

Explore More Software Engineering Skills→
davidrrowleydavidrrowley

azure-ai-voicelive-java

Enable real-time bidirectional voice conversations in Java via WebSocket streaming.

Community
Advanced
TugoukezhangTugoukezhang
8

openai-whisper-api

Transcribe audio files to text using the OpenAI Whisper API.

Community
Intermediate
microsoftmicrosoft
2.9k

azure-ai-voicelive-py

Build real-time voice AI applications in Python using the Azure Voice Live SDK.

Official
Intermediate
EmeaAppGbbEmeaAppGbb

Azure AI Projects Client Library Skill

Guide Azure AI Projects Python SDK usage for building and deploying AI applications.

Official
Advanced