# microsoft/call-center-ai

Send a phone call from AI agent, in an API call. Or, directly call the bot from the configured phone number!

Repository: https://github.com/microsoft/call-center-ai
Canonical: https://ross.abutalabs.com/products/call-center-ai
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-01T18:44:02+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 90, release rhythm 28, longevity 69
- inputs: {"age_days": 967, "days_push": 63, "days_rel": 463, "gap_med": 0, "n_releases_24m": 62}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6563, forks 779 (observed 2026-08-28T04:09:45.228802+00:00)

## What it is
An AI-powered call center service that lets you initiate or receive phone calls handled by an LLM-driven agent via a simple API call. Built on Azure and OpenAI GPT models, it supports inbound/outbound calls, SMS, real-time streaming, RAG over private data, and claim data collection.

## Use cases
- automate customer service phone calls with an AI agent
- have an AI bot place outbound calls to customers
- build an AI phone support line for IT helpdesk
- collect structured claim information over a phone call
- handle inbound support calls 24/7 with a voice bot
- add SMS fallback to AI voice conversations

## When to choose
- you need AI-driven inbound or outbound phone calls with minimal setup
- you want LLM voice agents integrated with Azure Communication Services and OpenAI
- you need claim/data collection during calls with RAG over internal documents
- you want multilingual, resumable, recorded voice conversations with human handoff

## When to avoid
- you need fully self-hosted telephony without Azure dependencies
- you only need text chatbots without voice or phone integration
- you require on-premises LLM inference rather than OpenAI models
- you need a simple IVR system without conversational AI

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, speech-recognition, tts, rag, api-framework, chatbot, webhook
- domain: artificial-intelligence, large-language-models
- platform: python, cloud, self-hosted
- tags: phone-calls, voice-agent, azure, openai, call-center, sms, telephony-api, ai-agents, telephony, automation, customer-service, docker

## Member repositories
- microsoft/call-center-ai (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:45.228802+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:03.084850+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/call-center-ai (fetched 2026-08-28T04:09:45.228802+00:00, sha b310dcad65c3)
- Data as of 2026-08-30T08:39:29.467469+00:00.