Azure-Samples/aisearch-openai-rag-audio

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.

57
/ 100
Established

This project helps businesses create interactive voice assistants that can answer questions using your specific company knowledge. You provide the assistant with your internal documents and a question via spoken language, and it responds aloud with an answer based on those documents, even citing its sources. It's designed for professionals who need to quickly access information from their internal knowledge base through natural voice commands.

547 stars.

Use this if you need to build a conversational AI agent that can understand spoken questions and provide spoken answers, drawing on your unique set of documents or data, rather than general internet knowledge.

Not ideal if your primary need is text-based search or if you don't require real-time spoken interactions and responses from your knowledge base.

knowledge-management customer-service internal-support voice-assistants document-qa
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

547

Forks

348

Language

Python

License

MIT

Last pushed

Nov 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Azure-Samples/aisearch-openai-rag-audio"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.