azure-openai

Integrate Azure OpenAI Realtime API with WebRTC for live voice conversations.

12|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/taiki-yoshida/claude-code-skills --skill azure-openai-taiki-yoshida
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: azure-openai
Source: https://github.com/taiki-yoshida/claude-code-skills/tree/main/azure-openai-gpt-realtime
Command: npx skills add https://github.com/taiki-yoshida/claude-code-skills --skill azure-openai-taiki-yoshida

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build voice-enabled AI experiences by integrating Azure OpenAI's Realtime API with WebRTC, providing a structured pattern to handle tokens, audio streaming, and prompts.

Core Features & Use Cases

  • Real-time token generation and session management for Azure OpenAI Realtime API.
  • WebRTC-based audio streaming between browser and backend with secure signaling.
  • Frontend configuration for system prompts, voice selection, pre-prompts, and transcripts.
  • Supports multiple gpt-realtime models across regions and use cases like voice assistants and live translation.

Quick Start

Install the skill by copying azure-openai into your Claude Code skills directory and restart Claude Code to enable real-time Azure OpenAI integration.

Frequently Asked Questions about azure-openai

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

FAQPage Schema
How do I integrate Azure OpenAI Realtime API with WebRTC for live voice conversations?

Integrating Azure OpenAI Realtime API with WebRTC involves backend token generation and frontend WebRTC signaling for audio streaming. This skill provides the structured pattern to manage secure sessions and live voice conversations.

What is needed to set up a secure token endpoint for Azure OpenAI voice apps?

To set up a secure token endpoint for Azure OpenAI voice apps, you need a backend service that handles real-time session token generation. This secures the WebRTC signaling between your frontend and the Azure OpenAI Realtime API.

Can I configure system prompts and voice selection for gpt-realtime models in a WebRTC client?

Yes, you can configure system prompts, voice selection, pre-prompts, and transcripts for gpt-realtime models within your WebRTC client. The skill includes frontend configuration patterns for managing these audio session parameters.

Does this approach support multiple gpt-realtime models across different regions?

Yes, the integration supports multiple gpt-realtime models across different regions. You can select specific models to handle use cases like voice assistants and live translation based on your deployment configuration.

What is the best way to handle audio streaming between a browser and Azure OpenAI?

The best way to handle audio streaming between a browser and Azure OpenAI is by using WebRTC for real-time communication. This skill provides the structured pattern for WebRTC audio streaming with secure signaling and backend token management.