A Spanish voice agent for outbound credit card campaigns
An AI voice agent that qualifies interest on 25,000 calls a day, handing warm leads to people.
An outbound campaign partner for one of Argentina's leading banksProblem statement
What the client was up against
The campaign ran with about 35 human operators making around 25,000 calls a day to qualify interest in a credit card offer. Cost per qualified lead was high and capacity was capped by headcount.
Our approach
How we approached it
- Integrated with the existing Neotel dialler over SIP
- Personalised each call from the lead file
- Tuned voice and prompts for Argentinian Spanish
- Handed qualified callers to the operator queue with a real call transfer
Solution we created
What we built
A white label voice agent with speech to text, a streaming language model and natural sounding speech. It answers in about a second, lets callers interrupt, logs every call and extracts outcomes automatically.
Agents in the system
The multi agent team behind it
SourcesNeotel over SIP, client PBX, lead CSV, monitoring dashboard
Voice agentRuns the conversation in Argentinian Spanish
Qualification agentCaptures interest and callbacks
Transfer agentHands warm leads to human operators
Post call agentLogs outcome, sentiment and commitments
People decideReview, approve and act
Voice agentRuns the conversation in Argentinian Spanish
Qualification agentCaptures interest and callbacks
Transfer agentHands warm leads to human operators
Post call agentLogs outcome, sentiment and commitments
Neotel over SIPclient PBXlead CSVmonitoring dashboard
What it was built to change
The outcome it is designed for
Far more qualified conversations per day at lower cost, with operators focused on warm leads.
This is a pilot without published results yet. We show the problem and the build, not numbers we have not measured.
Client names, detailed case studies, demos and references can be shared on request.
Looking for a similar solution?
Tell us your version of this problem. We will walk you through what we built and what a first pilot would look like for you.
