skills.rest
aiappsgbb
aiappsgbbOFFICIAL
Explore all skills by this author →
GitHub

foundry-voice-live

Migrate real-time voice agents to Azure Voice Live with session tuning.

5|2|Updated Apr 28, 2026
Search Tags:#azure#realtime#webrtc#voice-live#semantic vad#latency benchmarking#foundry agent
One-click install
npx skills add https://github.com/aiappsgbb/awesome-gbb --skill foundry-voice-live
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: foundry-voice-live
Source: https://github.com/aiappsgbb/awesome-gbb/tree/main/skills/foundry-voice-live
Command: npx skills add https://github.com/aiappsgbb/awesome-gbb --skill foundry-voice-live

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Builds real-time, low-latency voice agents on Azure AI Foundry by guiding developers to migrate from Azure OpenAI Realtime to Azure Voice Live (GA) with the correct session configuration, routing, and UI plumbing.

Core Features & Use Cases

  • Three-rung migration ladder: Provides copy-paste-ready connection differences for Realtime, Voice Live, and Voice Live routed through a Foundry Agent.
  • Voice Live session tuning: Sets azure_semantic_vad, server echo cancellation, azure deep noise suppression, and low-latency transcription with Azure Fast Transcription.
  • Agent routing via extra_query: Enables Foundry Agent activation by passing agent-id, agent-project-name, and agent-access-token on the Voice Live WebSocket.
  • Benchmarking latency with TTFA/TTFT: Defines a scenario matrix and measures request-to-audio and request-to-first-token latency patterns.
  • Gradio + FastRTC WebRTC UI integration: Shows how to wire a real-time browser microphone/speaker pipeline to the same Realtime event schema.

Quick Start

Use the foundry-voice-live skill to wire your WebRTC/Gradio demo to Azure Voice Live by switching MODE to demo and supplying AZURE_OPENAI_ENDPOINT and AZURE_VOICELIVE_ENDPOINT in your .env.

Frequently Asked Questions about foundry-voice-live

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

FAQPage Schema
How do I migrate from Azure OpenAI Realtime to Azure Voice Live for real-time voice agents?▼

To migrate to Azure Voice Live, switch your WebSocket connection to use the Voice Live GA parameters, specifically updating the websocket_base_url, api_version, and extra_query model or deployment handling to route real-time voice agents correctly.

How do I configure semantic VAD and noise reduction for Azure Voice Live sessions?▼

Configure semantic VAD and noise reduction by applying the session.update configuration to enable azure_semantic_vad, server echo cancellation, azure deep noise suppression, and low-latency transcription with Azure Fast Transcription.

How do I route Azure Voice Live through a Foundry Agent?▼

Route Azure Voice Live through a Foundry Agent by passing agent-id, agent-project-name, and agent-access-token via extra_query on the Voice Live WebSocket, ensuring proper access token scoping when using the agent rung.

What is the best way to benchmark real-time voice agent latency for TTFA and TTFT?▼

Benchmark real-time voice agent latency by defining a scenario matrix to measure request-to-audio and request-to-first-token latency patterns, systematically evaluating TTFA and TTFT metrics during Azure Voice Live interactions.

Can I use Gradio and FastRTC to build a WebRTC voice demo with Azure Voice Live?▼

Yes, you can wire a real-time browser microphone and speaker pipeline to the Realtime event schema by integrating Gradio and FastRTC WebRTC UI with Azure Voice Live endpoints for live voice demonstrations.

What connection parameters are required for Azure Voice Live GA?▼

Azure Voice Live GA requires correct connection parameters including websocket_base_url, api_version, and extra_query handling for model and deployment, alongside AZURE_OPENAI_ENDPOINT and AZURE_VOICELIVE_ENDPOINT environment variables.

Related Skills

Explore More Software Engineering Skills→
RobGibbensRobGibbens

azure-speech

Diagnose and optimize Azure AI Speech SDK, voice services, and deployments.

Community
Advanced
moongci38-ossmoongci38-oss

benchmark

Compare feature branch bundle size, test time, and API response time against a develop baseline.

Community
Advanced
pingqLINpingqLIN

huggingface-gradio

Create interactive ML demos and web UIs in Python with Gradio's Interface, Blocks, and ChatInterface components.

Community
Intermediate
taiki-yoshidataiki-yoshida
12

azure-openai

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

Community
Intermediate