Skip to content
buzinov.tech, home page
Client
Real estate agency, Kazakhstan
Industry
Real estate

Outbound voice agent for a sales team

Client call campaigns run end to end by a voice agent built on speech and language model services.

The problem

First-contact calls took hours of manager time, and most of them follow the same script.

What I built

A voice agent that works through a campaign list: it places the call, recognises what the client says, keeps the conversation on the script with a language model, answers with synthesised speech and records the outcome for the sales team.

The result

Client call campaigns for the real estate sales team ran end to end on the agent.

For the same agency I built automated sales call scoring. How such systems are built and what they cost is on the call and document analysis page.

Solution behind it

Pipelines with LLMs

Call and document analysis with LLMs

Pipelines that transcribe sales calls and score them against your checklist, or turn invoices and contracts into validated structured data.

  • Python
  • FastAPI
  • OpenAI API
  • Yandex SpeechKit

from$500

A process still runs on copy and paste?

Describe it in a few paragraphs. You get the approach, the first risk and a fixed estimate within 24 hours.